# What is FireCut?
**FireCut is a plugin for Adobe Premiere Pro and DaVinci Resolve that automates the boring stuff** so you can spend your energy on the interesting stuff. Our goal is to get you to your first cut in minutes, not hours.
With FireCut, you can remove silences from raw footage, detect chapters in your video, remove repetition (multiple takes of the script), edit multi-track videos like podcasts, and much more...
## 📖 How to use these docs
A lot of FireCut features will be obvious to you as an editor.
These docs will:
* Introduce all the features including the less obvious ones
* Show you best practices for getting the most out of them (and avoiding pitfalls!)
*Note: FireCut is developing at a rapid-fire pace, so these docs might occasionally be slightly outdated on the newest features. If you have any questions, message us on* [*Discord*](https://firecut.ai/accounts/join_discord/)*,* [*webchat*](https://firecut.ai/?action=chat) *or* [*email*](mailto:support@firecut.ai)*.*
## 🙏 One request: Please share feedback
FireCut was built hand-in-hand with video editors, and we've had beta testers from week 1 of development. This has been integral to building the tool we have today.
As you use FireCut, please share your feedback -- and in return, I promise to do my best to implement your suggestions!
Happy editing :)
**Suhail Idrees**\
Founder, FireCut AI
# Installing FireCut
{% hint style="info" %}
FireCut requires Adobe Premiere Pro 2022+
{% endhint %}
There are 3 ways to install FireCut. You can find the files for all 3 in your [dashboard](https://firecut.ai/accounts/dashboard/).
Once installed, restart Adobe Premiere Pro and go to the **Extensions** menu to find FireCut.
If you have any trouble getting started (e.g. you don't see FireCut in your extensions), [see this short FAQ](/overview-premiere-pro/faq#setting-up-firecut) to help you fix it!
### Uninstalling
**Windows:**
* Open Windows Explorer (e.g. by going to "This PC")
* Type %APPDATA%/FireCut in the address bar\
* Run the uninstaller (called "unins000.exe")\
* \[Optional] Delete the remaining files in the same folder **except for the "exports" and "Media" folders -- these might contain caption data or B-roll videos that you're using in your projects**
* **Hard reinstall:** To fully make sure there is no old or faulty version of FireCut present (e.g. if you're trying to do a hard reinstall of FireCut), find and delete any instances of the "com.firecut.base" folder from the following locations:
* C:\Users\\\\AppData\Roaming\Adobe\CEP\extensions
* C:\Program Files (x86)\Common Files\Adobe\CEP\extensions
* C:\Program Files\Common Files\Adobe\CEP\extensions
* C:\Program Files\Adobe\\\\CEP\extensions
**Mac:**
* Open a Finder window and go to /Library/Application Support/Adobe/CEP/extensions\
* Delete the "com.firecut.base" folder\
* **Hard reinstall:** To fully make sure there is no old or faulty version of FireCut present (e.g. if you're trying to do a hard reinstall of FireCut), find and delete any instances of the "com.firecut.base" folder from the following locations:
* \~/Library/Application Support/Adobe/CEP/extensions (also known as /Users/\ Show Package Contents. Then once inside, go to Contents/CEP/extensions
# Getting started
To get started:
* Download the FireCut installer (from your [dashboard](https://firecut.ai/accounts/dashboard/))
* Run the installer
* Restart Adobe Premiere Pro, open a project, go to Window -> Extensions -> FireCut, and enter your license key (from your [dashboard](https://firecut.ai/accounts/dashboard/))
If you have any trouble, see our [setup FAQs](https://learn.firecut.ai/overview/faq)
# Using FireCut
There are a few app-wide features helpful to know about when using FireCut:
### Main menu
FireCut's main menu is the "home" page for the plugin. It shows:
* Buttons for different features
* Button for the Settings menu
* At the top: a link to FireCut's homepage, an "Undo" button, a "Reload plugin" button, and (when an update is available) an "Update" button
### Settings menu
The Settings menu is used for verifying your license key and managing any app-wide settings.
### Undo
The Undo button gives you a way to roll back any changes made by a FireCut feature.
It will save a copy of your sequence before operations like removing silences. If you wish to undo the operation, just click on "Undo" at the top of FireCut and confirm. Please note: Using Ctrl+Z or Cmd+Z for rolling back FireCut operations is not recommended. **The "Undo" button is the most reliable way of rolling back these changes.**
### Reload plugin
The Reload plugin button is a convenient way to abort / reset the plugin in case you run into any issues.
You should not need to use this button often, but it can be helpful in case the plugin freezes / crashes, or is causing any issues with your timeline. It has the same effect as closing the plugin window and re-opening it from Window > Extensions > FireCut.
### Update to the latest version
FireCut will show you when a version update is available.
Just click this button and FireCut will download the latest installer file (.exe or .pkg, depending on your platform). The installation works the same as how you installed FireCut the first time; it will just replace the old version. Run the installed and restart Premiere Pro to start using the latest version.
If this method doesn't work or you would prefer to use a different installation method, you can always find the latest FireCut installers in your [dashboard](https://firecut.ai/accounts/dashboard).
### Share feedback
At FireCut, we love feedback so much that we built a super easy way to share it without leaving Premiere Pro!
The "Share feedback" menu lets you report bugs, request new features and share any other feedback directly from Premiere Pro. Your feedback goes straight to our public feedback board hosted at Canny ([link](https://firecut.canny.io/feedback)).
# FAQ
## Setting up FireCut
I installed FireCut, but it's nowhere on my desktop
FireCut is a plugin for Adobe Premiere Pro 2022+ and so it requires this software in order to run.
If you'd like to use FireCut with other editing tools such as Final Cut Pro or DaVinci Resolve, please [sign up to FireCut Desktop](https://forms.gle/RaL7P5ttCpGJCf33A) (it's currently free while in beta!)
I installed FireCut, but the Window > Extensions menu in Premiere Pro is greyed out
Try opening a project. The Window menu is only available if a project is open in Premiere Pro.
I installed FireCut, but nothing happens when I click on Window > Extensions > FireCut
Please try uninstalling and reinstalling the latest version of FireCut.
* To uninstall, follow the instructions [here](https://learn.firecut.ai/overview/installing-firecut) **including the "hard reinstall" step**
* To install the latest version, get it from the [downloads page](https://firecut.ai/downloads/)
I can't download the FireCut installer for Mac (.pkg)
There is a reported issue in downloading the .pkg installer file on Firefox which shows the code on the screen instead of downloading the file. Please try Chrome or another browser instead (you can use this link to avoid signing in: )
I purchased a license key but it doesn't show up in my dashboard
If you went through a Stripe checkout page, but don't see a license key in your dashboard then it's usually one of 2 issues:
* **(1) The license keys table is missing:** Your browser is blocking the license key from being displayed --> Try a different browser OR reduce the screen size to force your browser to show the mobile version of the page\
* **(2) You get shown the pricing page again in your dashboard:** Either your transaction didn't go through (more likely), or we had an issue processing the confirmation message from Stripe (technically possible, but very unlikely) --> Please ensure you entered the correct details on the Stripe checkout page, and saw a confirmation message that the details were accepted. If no luck, email 
The FireCut window opens, but the plugin won't load or it's showing an error I haven't seen before
* **The first thing to try is to change your version of the FireCut plugin:**
* If you're on an old version, try the latest version from [here](https://firecut.ai/downloads/).
* If that doesn't work (or if the issue came up after upgrading to the latest version), just downgrade to an older version of the plugin by getting it from [here](https://firecut.ai/downloads/old/premiere/). As we publish new releases often, we recommend downgrading to a version that is 3-5 versions before your current one.
* **If that doesn't work, try changing your version of Premiere Pro:**
* If you're on an old version (e.g. from 2 years ago), try the latest version of Premiere Pro.
* If you're already on the latest Premiere Pro version, try downgrading it to an older version (as it's possible that a breaking change in the latest version broke compatibility with your version of the plugin).
If that doesn't solve your problem, please [contact support](#contact-support).
## Captions
How can I edit captions created with FireCut?
FireCut creates captions as PNG images. In order to edit any captions, simply select the clip(s) you want to edit, and then in FireCut click **Add captions > Edit selected captions**
This will load up the selected captions into the editing panel. If you want to load the full transcript, just click **Load full transcript**
You are now free to make any changes in this panel. To update the captions, click **Add styled captions to sequence.** This will add the updated captions in a new track to ensure your original captions are not over-written or affected in any way.
My caption clips have diagonal stripes / are not rendering
This occasionally happens if you re-open a project that contains FireCut styled captions, and is usually caused by Premiere not opening the caption image files correctly.
The fix is simple [(see 2 min video)](https://youtu.be/BkcCOUmdcyU)
1. Right-click one of the caption clips that has those diagonal stripes > **Reveal in Project**\
2. This will show the clip in the Project panel, and also open the Bin this clip sits inside. Now, in the Project panel, **select ALL the caption clips in the opened Bin with Ctrl+A or Cmd+A (no need to do them one-by-one!)** and then **Right-click > Modify > Interpret footage...**\
3. Then click **OK** without making any changes\
This forces Premiere Pro to re-ingest the clips and open them correctly.
How can I share my Styled caption presets with others?
Use this method for sharing your Presets: [Sharing your preset style with others](https://app.gitbook.com/o/JLshJCMS5EazXVAAwAUd/s/WDn6n1C7MKZBHdDcmm6f/~/edit/~/changes/97/features/add-captions#sharing-your-style-preset-with-others)
***
***Old method:***
Your caption presets are stored in this file:
* Windows: `%APPDATA%\FireCut\caption_presets_custom.json` (or full version: `C:\Users\\AppData\Roaming\FireCut\caption_presets_custom.json`)
* Mac: `~/Library/Application Support/FireCut/caption_presets_custom.json` (or full version: `/Users//Library/Application Support/FireCut/caption_presets_custom.json`)
To share them between users/devices, just copy this file across to the new user, making a backup of the existing file if required.
Will I lose my Styled caption presets if I change my license key?
No, your caption presets are saved to your device. They will be available even if you change your license key.
However, this means you will lose access to them if you change devices. To copy these presets to your new device, see the other FAQ above: "How can I share my Styled caption presets with others?"
## Common Errors
I'm getting the error `ERROR: Error reaching the server for license key validation. Please ensure you are connected to the internet."
This indicates a network issue on your side (e.g. your firewall, ISP, VPN, etc.).
Some suggestions for fixing this:
1. Check your firewall settings to explicitly allow Premiere Pro, or disable the firewall altogether for a few minutes
2. Try a different Wi-Fi network / your phone's hotspot
3. If you are on a work computer / a computer where some websites might be disabled, try a different computer or network
4. Restart your device
5. Fully uninstall and reinstall FireCut with the instructions here: Whenever I run a FireCut feature, it takes a long time to export/encode my audio for analysis
The first step for almost every FireCut feature is to export the audio from your sequence. The speed of this process depends on your source audio file format (mainly: is it compressed or uncompressed?), and the number of non-empty audio tracks being mixed together.
The easiest way to speed up this process for sequences that have compressed source audio is to use the "Render and Replace" function in Premiere Pro to uncompress (or "extract") the audio once.
Here's a video showing the process: [\[Link to video\]](https://youtu.be/W3M6w_5N2aA)
**Steps:**
1. Unlink your audio/video clips
2. Select your audio clips → right-click → Render and replace
When the progress bar completes, the audio clips in your sequence will be replaced by "extracted" uncompressed WAV versions which are much faster for Premiere Pro to work with. This means your timeline will be faster, and your exports will be faster.
Note: This will only help for source audio formats that are compressed (e.g. MP3, AAC). It's sometimes unclear if an audio is compressed or not just by looking at the file extension so I also show at the start of the video how to check if this is the case by using Media file properties.
I cannot open dropdowns to change settings like language or font
This is a known bug in Premiere Pro 2025 on MacOS. It occurs only when the plugin panel's height is too small.
Some workarounds:
* Increase the panel's height. Above a certain point, the dropdown should work normally
* Click on the dropdown to "focus" it. Once focused, you can type in your desired language/font or use keyboard up/down arrow keys to find it
I'm getting the "Unable to connect to Premiere Pro" error.
This means Premiere Pro is unresponsive/occupied with other tasks - it could happen for a number of reasons but we suggest trying to disable other extensions which might be using PP's API, or resetting some settings to default by restarting with [Shift](https://helpx.adobe.com/sg/media-encoder/using/reset-and-restore-preferences.html), or switching to a different PP version.
I can't find my locally installed font in the plugin. What should I do?
If your preferred font isn't appearing in the FireCut interface, please follow these troubleshooting steps:
* Verify Installation: Confirm the font is properly installed on your operating system. A quick way to check is to see if it appears and works in other applications like Microsoft Word or Apple Pages.
* Restart Premiere Pro: Sometimes Adobe Premiere Pro needs a fresh launch to index newly installed system fonts. Close the program entirely and reopen it.
* Search and Scroll:
* Try typing the exact name of the font directly into the plugin's font dropdown menu.
* Manually scroll through the list to look for it under the System Fonts category.
* Contact Support: If the font still refuses to show up, we want to help. Please email the font file (e.g., `.ttf`, `.otf`, or `.ttc` formats) to so our team can investigate the compatibility.
## Other
How do I change my subscription (e.g. change from Starter to Pro, cancel, etc.)?
Go to your [dashboard](https://firecut.ai/accounts/dashboard/) and click on the Manage button shown next to your license key.
I cannot see some features (such as Captions) in the FireCut panel
Check which plan you have (e.g. Starter, Pro) from your dashboard (). The available features depend on which plan you have. You can see the details of features for each plan on the Pricing page on our website ()
Where do I share feedback, feature requests, issues, etc.?
There are multiple ways to do this so there's no excuse not to share :)
* Message in our Discord server (link in your [dashboard](https://firecut.ai/accounts/dashboard/))
* Email
* Use the "Share feedback" button inside the FireCut panel (in Premiere Pro)
I would like to share it with my audience. Can I partner with you?
Yes! You can join our affiliate program through this link I would like to share it with friends / family. Can I get a referral code?
You can use a referral code for sharing with other people. You will get an email when you become eligible for this program (typically after your first payment has been made), and you will be able to click the "Refer a friend" button in your dashboard
How can I stay up to date on new and upcoming features?
The best way is to read our newsletter. You should get this if you are signed up for a plan, please do check your spam folder if you can't find an email (we typically email weekly).
How is my "usage" calculated in the dashboard?
FireCut has a monthly usage limit for certain features, marked with an asterisk (\*) on our pricing page (). The usage refers to the duration of audio/video that is processed, i.e. creating captions for a 1 hour timeline will use 1 hour from this usage.
How many devices can I use with a FireCut license?
Each FireCut license key is individual, and is linked to one device at a time. If you would like to switch between multiple devices you are using for yourself, you can do so by going to your dashboard -> clicking "Unlink" -> then entering the same license key on your new device. However, as licenses are individual please do not share your license key with others as this is against our terms.
I am a student. Can I get a discount?
Sure - follow the instructions here: Where are your terms of service?
You can find our terms of service here: Is storyblocks included in my subscription?
Yes. It is included in your FireCut subscription. You can refer to our EULA which has the rules for Storyblocks content I need to change details on my invoice. How can I do that?
We are fully self-service which means you have full control over your plans and account details. You can manage everything from your dashboard. -> Manage -> Update payment details, and add any information here that you would like to add to your invoice
## Contact support
If you still have questions, you can always reach out to us at
# Installing FireCut
{% hint style="info" %}
FireCut requires DaVinci Resolve 20+, and supports both Free and Studio versions
{% endhint %}
## Windows and Mac
1. **Download FireCut** for your platform using the links in your [dashboard](https://firecut.ai/accounts/dashboard/).
2. **Close DaVinci Resolve**, then install and open FireCut.
3. **Copy your license key** from your [dashboard](https://firecut.ai/accounts/dashboard/). (If you haven't yet purchased a key, you can start a free trial [here](https://firecut.ai/pricing/). Once you have checked out your free trial through Stripe, you will see your license key in your dashboard.) Paste this key into FireCut → Settings menu.
4. **Open DaVinci Resolve**, and connect it to FireCut from Workspace → Scripts → FireCut.
## Linux
FireCut for DaVinci Resolve is available on Linux as a Debian package (.deb). This package can be installed on any Debian-based distribution, such as Ubuntu, Pop!\_OS, or Linux Mint. Afterwards, you'll see the FireCut icon in your applications menu, or you can launch it via the terminal (`firecut-davinci`).
RPM-based distributions like Fedora can install the Debian package using the `alien` utility, which converts .deb packages to .rpm format. The documentation for `alien` can be found [here](https://wiki.debian.org/Alien).
Arch-based distributions, including Manjaro, can also install the Debian package using the `debtap` utility, which can be installed from the AUR (Arch User Repository). The documentation for `debtap` can be found [here](https://github.com/helixarch/debtap?tab=readme-ov-file#debtap).
Automatic updating is not available for Linux, so keep an eye on the homepage for new releases, or join our Discord server to get notified when a new version is released.
## Installation problems?
If you have any trouble with installing / opening FireCut, try the suggestions in our [troubleshooting page](/overview-davinci-resolve/troubleshooting).
# Troubleshooting
## Setup issues and how to fix them
I installed FireCut but I don't know how to open it
First, let's make sure you have completed the installation:
* **Mac:** You opened the .dmg file and copied FireCut from the .dmg to your Applications folder
* **Win:** You ran the .exe installer and it successfully finished installing FireCut
### Main way of opening FireCut
The main way to open FireCut is to go to DaVinci Resolve -> Workspace -> Scripts -> FireCut
This will open the FireCut window.
### If that didn't work: alternative method of opening FireCut
If the main method did not work for you, you can also open FireCut by just running the app directly
* **Mac:** Open your Applications folder and open "FireCut for DaVinci Resolve"
* **Win:** When you run the installer, it will automatically open FireCut for you. If you want to open it later, you have 3 options:
* Open "FireCut for DaVinci Resolve" from your Desktop (this shortcut was made during installation)
* Open this file: `C:\Users\\AppData\Local\FireCut-DaVinci\FireCut for DaVinci Resolve.exe`
* Just run the installer again
This will open the FireCut window.
If you still don't have any luck in opening the FireCut window, please let us know in our Discord or by emailing
### **After FireCut opens**
This is where you can review the EULA and then you will see this Settings screen for entering your license key:
You can find your license key in your dashboard (), just copy and paste it into this menu and click on "Verify"
FireCut missing from Workspace -> Scripts
### Why this can happen
* FireCut is not properly installed
* You just need a restart of your computer
### How to fix it
* First, check if FireCut is installed by going to these folders to check if the file **FireCut.lua** exists:
* Mac: `~/Library/Application Support/Blackmagic Design/DaVinci Resolve/Fusion/Scripts/Utility`
* *You can go to this path by opening Finder, then pressing `Cmd + Shift + G` to open Go to Folder... (or find this command from the Go menu at the top), then copy/pasting the path and pressing Enter.*\
* Win: `%AppData%\Blackmagic Design\DaVinci Resolve\Support\Fusion\Scripts\Utility`
* *You can go here by opening File Explorer, then copy/pasting the path into the path bar*\
* If you cannot find **FireCut.lua** in any of these locations, then run the FireCut installer again and open FireCut for DaVinci Resolve. This app will copy the **FireCut.lua** file to the correct location on startup. Then check these paths again.
* If you still do not see FireCut in your Scripts after a restart, please get in touch with us in our FireCut for DaVinci Resolve Discord (link in your email) or by emailing FireCut stuck at "Not connected to DaVinci Resolve"
### Why this can happen
* You successfully opened the **FireCut for DaVinci Resolve** app, but have not yet run the FireCut script from DaVinci Resolve. This step is ESSENTIAL as otherwise the FireCut app cannot connect to your DaVinci project and timeline
### How to fix it
* Simply open DaVinci Resolve, then go to **Workspace -> Scripts -> FireCut**. This should establish a connection to the **FireCut for DaVinci Resolve** app
* In the future, you should also be able to launch FireCut simply by doing this same process from DaVinci Resolve. It is not necessary to have the **FireCut for DaVinci Resolve** app open beforehand
I updated FireCut to a new version and now it doesn't work
We're developing FireCut at a rapid pace, typically with multiple releases a week! This means occasionally some features may work differently than they previously did or break altogether.
If this happens, it's super easy to revert to a previous version that worked for you. Just get it from here:
## Other issues
If you face any other issues with setup that are not listed here, please message us in our FireCut for DaVinci Resolve Discord (link in your email) or email
# Remove silences
## ❓ What is it?
Almost every edit starts with raw footage that has useless, silent portions. **Remove silences** cuts all these silences out with only a few clicks.
## 🤔 How does it work?
Silence cutting in FireCut is powerful and flexible.
* You specify which audio tracks to use as **guidance tracks**
* **When *****all***** guidance tracks are silent, that portion of your sequence is cut out** i.e., all tracks are cut. This is because you might have your "good" audio on many different tracks / clips, and they might not even by linked to your video. This does not matter for FireCut, as long as you select the right guidance audio tracks
{% embed url="" %}
{% embed url="" %}
{% hint style="info" %}
For your first silence cut, you should apply it to a small part of your sequence (5 mins) to see what it actually does.
{% endhint %}
## ⚒️ Basic vs. Advanced mode
* **Basic:** One-click operation with 1 main setting: **cutting tightness**. If you want some short gaps before and after silences in the result, then choose a loose cut. If you prefer a fast-paced video with very sharp cuts, then pick a tight cut. When you click "Go", FireCut will detect silences and cut them out, all in one go.
* **Advanced:** Three-step operation to allow greater customisability:
1. Detect silences based on various settings
2. Review silences in a list, and customise which ones to keep, how much padding to add
3. Cut out these silences
{% hint style="info" %}
If you're cutting silences from a large sequence (e.g. 1 hour of footage), you should use **Advanced** mode so you can preview and fine-tune the output before making the cuts
{% endhint %}
## ⚙️ Settings
Both modes have:
1. **Silence guidance audio tracks:** The audio tracks you want FireCut to listen to for silences. Whenever all of these tracks are silent, that portion of the sequence will be marked for cutting.
2. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
3. **Speech detection:** Experimental feature which detects portions of your sequence which are not silent, but might not have any words being spoken in them. This feature is for removing background noise which is above the silence detection threshold.
4. **Cutting algorithm:** How FireCut performs the cuts (this does not affect *where* the cuts actually happen). Over time, we release newer and faster algorithms. Currently we have:
* **Original:** Most reliable but slow, best for **short sequences** (<10 mins scope, <50 silences)
* **Rapid:** Faster and fairly reliable, best for **longer sequences** (10-30 mins, 50-100 silences)
* **Turbo:** Fastest but quite experimental as of late July, best for **very long sequences** (30 mins to multiple hours, 100+ silences)
If you're using **Basic** mode, there is just 1 main setting that determines how silences are identified: the silence cutting tightness. You should start with a **loose cut**, and repeat if you need for tighter cuts. After a few tries, you'll find a value of tightness that works well for you!
For **Advanced** mode, there are a few extra options on detecting silences:
* **Silence threshold:** This is the audio level in [dBFS (decibels relative to full scale)](https://en.wikipedia.org/wiki/DBFS) below which FireCut will deem your sequence to be silent. If you're not familiar with dBFS, it is the same scale you see in the Premiere Pro audio level indicator. It has a maximum value of 0 dBFS (which means audio levels are usually negative). The right threshold depends on your audio source but **a good starting point is -30 dBFS**
* **Auto-detection of silence threshold:** FireCut can recommend you a good threshold to use. It does so by analysing the audio of your sequence (the portion in scope) and plotting the frequency of different loudness levels. These are then shown in a small chart under the threshold slider. In this chart you will typically see **two peaks:**
* The peak on the right (at a higher dBFS loudness level) is your useful audio e.g., your speaker, and will likely be around -20 dBFS
* The peak on the left (at a lower dBFS loudness level around -50 dBFS) represents the silent portions in your scope
Note: **This chart shows how common the different loudness levels are**, so for example if you are speaking half the time at -20 dBFS, and are silent for the remaining half of the time with a background noise of -50 dBFS, then you will see two peaks in this chart of roughly the same size at -20 and -50 dBFS. **You should pick a threshold between these two values (such as -35 dBFS) so that FireCut picks out only the portions *****below***** that threshold to be silences.**
* **Minimum silence duration:** This is the minimum duration for which your audio needs to be below the threshold in order to be detected as a silence portion that should be cut. While FireCut's flexibility allows very small values, this is **not** recommended because it will create lots of small cuts even at breaks between words, which is usually undesirable! **A good starting point is 750ms**
For **Advanced** mode, once silence detection is done, you can review and modify the list of detected silences:
* **Cycle through silences:** You can click on any of the silences (or the next / previous silence buttons) to see in your timeline. Clicking the "X" next to any silence will remove it from consideration, and it will not be cut.
* **Padding:** If you find that the silence detection was too "aggressive" (e.g. it's marked the start/ends of words as silences), this can be fixed by increasing padding. Padding is basically just extra space you allow for your clips. Increasing it has the effect of pretending the silence was shorter than what was detected, and so it leaves some extra breathing room between cuts. Some detected silences might not be cut at all when you increase padding (because the padding is more than the duration of the silence). **A good starting point for padding is 250ms on start AND 250ms on end**
* **J-cuts offset:** Increase this above 0 frames to create J-cuts (i.e. cutting the audio earlier than the video). As the diagram in this review screen shows, the offset is actually applied to the video clip, not the audio clip, so your silences will still be cut in the same places. This is done to ensure you don't accidentally cut the starts/ends of sentences. [More details on J-cuts here.](/features/remove-silences/j-cuts)
## 💡 Tips for best outcomes
* **Get familiar with Advanced mode early.** It offers much greater flexibility!
* **Don't use settings that will create hundreds of cuts**, which are often undesirable and will take too much detection / processing time. For example:
* Don't set the detection threshold (dBFS) too high. Going over higher than -30 dBFS is not recommended
* Keep the minimum silence duration above 750ms
* Always add some padding before cutting, this might even get rid of the shortest silences
* **Try your settings on a small portion of your sequence** before processing hours of footage
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"It cut out my entire sequence"** --> The detection threshold was too high / the tightness was too tight. Try Advanced mode with an auto-detected threshold (and move it lower if the suggested value seems too high), and set the min silence duration at least 750ms.
* **"It slowed down my Premiere Pro project"** --> This is a Premiere Pro issue and can happen if you make too many cuts (i.e. typically 500+ cuts, but depends on your system resources such as RAM). Premiere Pro timelines work slower when you have more clips in them. The recommended fix is to adjust your silence cutting settings to result in fewer cuts by doing Advanced mode -> increase both padding and minimum silence duration
* **"It slows down over time when processing long sequences"** --> This happens with Original and Rapid algorithms because the number of clips on your timeline increases as cuts are made, slowing down Premiere Pro. If you're experiencing very long processing times (e.g. 30+ mins), then it's a sign that:
* You are likely cutting more silences than you need (slowdown typically happens when you're cutting 200+ silences)
* You should try Turbo mode
* **"I had an issue with Turbo mode"** --> This feature is brand new, and we want to fix whatever caused the issue for you! Please use the "Share feedback" button inside FireCut / email
# J-cuts
## ❓ What is it?
A J-cut is a type of cut between 2 clips on a timeline where the audio cuts to the next clip **before** the video does.
The key metric is the "**offset**" (i.e. **how** **much earlier** does the audio cut vs. the video?), typically measured in frames. The 2 most common applications of J-cuts are:
* **1-10 frames offset for making cuts smoother:** Cuts in the video can often appear "jumpy" especially if you have a lot of them. Adding a slight offset where the audio comes in earlier can make the cuts feel smoother. This creates a subliminal effect of making the video "follow" the audio.
* **10+ frames offset as a stylistic touch:** This is an artistic application of J-cuts, where the editor "sets the scene" with audio before the video comes in, e.g. hearing the sound of rain on black video before the actual footage even starts, hearing an interviewee start speaking in a documentary before switching the camera to them, etc.
{% hint style="info" %}
Note: J-cuts are available as part of the **Advanced** mode in Remove Silences
{% endhint %}
## 🤔 How does it work?
J-cuts in FireCut are a part of the advanced "remove silences" feature.
* You specify which audio tracks to use as **guidance tracks**
* **When *****all***** guidance tracks are silent, that portion of your sequence is cut out** i.e., all tracks are cut. This is because you might have your "good" audio on many different tracks / clips, and they might not even by linked to your video. This does not matter for FireCut, as long as you select the right guidance audio tracks
* **You specify what J-cut offset to apply** (0 frames = no J-cut) and FireCut accordingly changes where your video and audio are cut to create that offset. The offset is actually applied to the video clip, not the audio clip, so your silences will still be cut in the same places. This is done to ensure you don't accidentally cut the starts/ends of sentences.
## ⚙️ Settings
J-cuts only have 1 setting (as part of the review screen in **Remove silences > Advanced mode**):
1. **Offset:** This is the number of frames by which the cut between the audio and video will be offset. A number greater than 0 will cause the audio to be cut earlier than the video by that many frames. Leave this at 0 if you don't want J-cuts.
## 💡 Tips for best outcomes
* **Don't use settings that will create hundreds of cuts** (and result in lots of short clips), which are often undesirable and will take too much detection / processing time. For example:
* Don't set the detection threshold (dBFS) too high. Going over higher than -30 dBFS is not recommended
* Keep the minimum silence duration above 750ms
* Always add some padding before cutting, this might even get rid of the shortest silences
* **Try your settings on a small portion of your sequence** before processing hours of footage
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"It cut out my entire sequence"** --> The detection threshold was too high / the tightness was too tight. Try Advanced mode with an auto-detected threshold (and move it lower if the suggested value seems too high), and set the min silence duration at least 750ms.
* **"It slows down over time when processing long sequences"** --> This happens with Original and Rapid algorithms because the number of clips on your timeline increases as cuts are made, slowing down Premiere Pro. If you're experiencing very long processing times (e.g. 30+ mins), then it's a sign that:
* You are likely cutting more silences than you need (slowdown typically happens when you're cutting 200+ silences)
* You should try Turbo mode
* **"I had an issue with Turbo mode"** --> This feature is brand new, and we want to fix whatever caused the issue for you! Please use the "Share feedback" button inside FireCut / email
# Remove filler words
## ❓ What is it?
Remove filler words helps you find words like "umm" and "uhh" in your sequence that are typically unwanted, and then helps you cut them out.
## 🤔 How does it work?
This feature:
* Finds the filler words in your sequence
* Shows these filler words in context of the rest of your sequence. You can right-click words to select/deselect them for deletion
* Lets you place markers in the sequence where these words occur, if you only want to mark them and double check them later
* Lets you cut them out automatically
{% embed url="" %}
## ⚙️ Settings
There are two main settings:
1. **Filler words guidance audio tracks:** The audio tracks you want FireCut to listen to for filler words. Whenever all of these tracks are silent, that portion of the sequence will be marked for cutting.
2. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
## 💡 Tips for best outcomes
* **Make sure your audio does not have long silences**, and any music / sound effects are muted
* **Remove any repetitions first**, as FireCut might not transcribe multiple instances of the same text
* **Feel free to work in the timeline**, while FireCut is processing your audio -- however, changing the timing of your clips might cause the transcription to be misaligned (FireCut's transcription follows your **sequence**'s timecode, not individual clips)
## 🙋♂️ Common questions, issues, watch-outs
* **"It did not find all the filler words"** ->
* This feature is currently in beta and might miss some instances of filler words. If you do find that the detection is not accurate, please report it to us so we can fix it :) ->
# Remove repetition
## ❓ What is it?
Certain types of video tend to have a lot of repetition in the raw footage (e.g., single speaker setup where they are recording a script, doing multiple "takes" of certain phrases).
**Remove repetition** detects when the speaker is repeating phrases in the video, and allows you to select one "take" to keep while deleting the others.
## 🤔 How does it work?
Remove repetition in FireCut:
* Analyses the words being spoken in the selected portion of your sequence to detect when phrases are being repeated
* For each phrase that is being repeated, shows you a list of all sections where you have a "take" of that phrase -- the words might vary slightly between these "takes", so FireCut does its best to pick up approximate matches as well as exact matches
* Lets you preview each "take" by clicking on it
* Once you know which "take" you want to keep (this usually tends to be the last one in each set, as the speaker will probably keep going until they think they've recorded a good "take"), you can select it with the tick button -- this deletes all the other "takes" in that set
* Keep going through the phrases until you've selected your favourite "take" for each
{% embed url="" %}
## ⚙️ Settings
There are 3 main settings for remove repetition:
1. **Mode:**
* Basic mode is a "done for you" solution that uses the optimal sensitivity to use when finding repetition
* Advanced mode (default) lets you investigate your transcript and customise repetition detection settings, such as tolerance and search radius
2. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
3. **Language:** We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because [training sets for AI tend to be in English](https://www.wired.com/story/chatgpt-non-english-languages-ai-revolution/). On occasion, this might cause the operation to fail -- please do let us know () if this happens, so we can improve it for you!
## ⚒️ Advanced mode
If you choose advanced mode, you get 4 further settings to fine-tune detection of repeated phrases:
* **Minimum phrase size:** The minimum number of words that have to be repeated in order to be detected as a "match"
* **Tolerance:** How loose of a match will be detected as a repetition.
* 0% means only exact matches will be detected
* 80% means even loose repetitions will be detected (this might catch some "false positives", i.e. phrases that were only slightly similar)
* **Search radius:** How far away to look for a match. If you increase this, FireCut will look for repetitions even far away from your initial phrase.
* **Extend last occurrence of each phrase:** How FireCut should determine where exactly the last occurrence ends. Let's say we found 3 repetitions of a phrase. We know that the first 2 occurrences of the phrase end whenever the next occurrence starts. However, there's no fixed ending point like this for the last occurrence. This settings lets you customise how to define that ending point:
* Extend to end of sentence: This will define the next fullstop/period as the ending point
* Use the length of the longest occurrence: This will use the longest occurrence so far, and make the assumption that the last occurrence is of that length as well. This is unlikely to be 100% exact, but you might prefer this behaviour if you know the phrases are similar lengths and don't necessarily end in a fullstop.
* Use phrase size: This uses your predefined "minimum phrase size" setting above
## 💡 Tips for best outcomes
{% hint style="info" %}
Because this feature's use case is to remove repeated takes, it will detect repetition only when it is **consecutive** (i.e., the speaker has done a few takes right next to each other). If you do a second take 5 minutes after the first one, and there are other things being discussed in between, FireCut won't mark these.
{% endhint %}
* **Before selecting your favourite take**, make sure FireCut has marked the start and end of that take exactly as you want it (by clicking on the take in the list, which will mark it on your timeline)
* **After completing the process, do a double-check** to ensure your take has the right start and end points -- occasionally, FireCut might chop off starts / ends of words
* **Make sure your audio is loud and clear**, with any music / sound effects muted
* **Try it on a short section of your timeline first** to get familiar with the tool; processing larger sequences can take a while
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"It didn't detect all the repetitions"** --> Make sure you have a clear speaker in the audio so that your script can be picked up and analysed. If there are any sound effects, multiple speakers, music, noise, etc., this can throw off the analysis in some occasions
* **"It didn't work on my non-English video"** --> Please drop a note at . We are keen to make sure this feature works reliably on all supported languages!
# Remove profanity
## ❓ What is it?
Some videos can have profanity (curse words) in them, which we might want to edit out. **Remove profanity** detects when those words are being spoken and automatically mutes them or lays a beeping sound over them.
## 🤔 How does it work?
Profanity removal in FireCut:
* Analyses the words being spoken in the selected portion of your sequence to detect profanity in the selected language.
* Lets you add or omit your custom profanity words with **Custom blocklist** and **Custom allowlist** options.
* Lets you individually select or deselect found profanity words.
* Lets you choose between **muting** & **bleeping** methods of removing profanity words.
* Various overlaying sounds are available for the bleeping method: beep, quack, dolphin & ahooga
* Updates the timeline audio track of your sequence where the selected profanity words are being spoken by either muting the track or overlaying it with the selected beeping sound. Note: ALL audio tracks are affected when running this feature.
{% embed url="" %}
## ⚙️ Settings
* **Scope:** You can decide whether to run the operation on your Full sequence or only on a certain portion that you specify with In / Out points (you can place these in your sequence using the I and O hotkeys)
* **Language:** Language that is spoken in the scoped video clip. We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because training sets for AI tend to be in English. On occasion, this might cause the operation to fail -- please do let us know () if this happens, so we can improve it for you!
* **Profanity list:** Predefined list of profanity words that are to be matched in the video.
* **Mute or bleep:** Profanity removal method: mute or bleep. Mute only mutes the profanity words in the audio while Bleep mutes the words and also overlays them with the selected bleeping sound.
* **Bleep SFX sample:** Bleeping sound that gets overlaid over the profanity words: beep, quack, dolphin & ahooga. This option is only available when the Bleep method is selected.
* **Custom blocklist:** List of additional profanity words that are included in the profanity search.
* **Custom allowlist:** List of profanity words that are excluded in the profanity search.
## 💡 Tips for best outcomes
* **Make sure your audio is loud and clear**, with any music / sound effects muted
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"It didn't detect all the profanity"** --> Make sure you have a clear speaker in the audio so that your script can be picked up and analysed. If there are any sound effects, multiple speakers, music, noise, etc., this can throw off the analysis in some occasions
* **"It didn't work on my non-English video"** --> Please drop a note at . We are keen to make sure this feature works reliably on all supported languages!
# Add voiceover
## ❓ What is it?
Convert your text into natural-sounding speech with customizable voices and settings.
This is especially useful for narrations, explainers, or adding context to silent footage. With flexible controls for voice selection, pace, tone, and character tuning, you can fine-tune the output to match your project’s style.
## 🤔 How does it work?
To use the Add voiceover feature:
1. Open the **Add voiceover** panel in FireCut.
2. Enter the text you want to convert into audio.
3. Select a **Voice type** (e.g. Alice, John) and click the Play button to preview it.
4. Adjust the **Speed** if needed.
5. Choose the **Language** of the voice.
6. Toggle on **Use advanced controls** for fine-grained control (optional).
7. Choose the **output audio track**, and optionally turn on "**Add captions**".
8. Click **Generate audio** to create your voiceover.
The generated audio will saved to your selected location on disk, and inserted on your timeline.
## ⚙️ Settings
* **Voice settings**
* **Voice type**: Pick from a list of available voices. Each voice has a different tone and personality.
* **Speed**: Adjust how fast or slow the voice reads your text (default is 1.0x).
* **Language**: Choose the language of your voice to match your script.
* **Use advanced controls**: Enable this toggle to access additional voice customization options to fine-tune the voice with the following parameters:
* **Stability**: Controls the consistency of the voice’s pronunciation and tone. Lower values make the voice more expressive but less predictable.
* **Similarity boost**: Increases the accuracy of mimicking the selected voice’s original character.
* **Style**: Adjusts the level of emotional expression. Higher values add more emphasis and variation.
* **Enable speaker boost**: Enhances the loudness and clarity of the voice.
* **Output settings**
* **Insert on audio track**: Choose where the voiceover will be placed on your timeline.
* **Add captions**: Optionally generate captions for the voiceover text.
* **Save location**: Specify where the generated audio file should be saved locally.
## 💡 Tips for best outcomes
* Keep your text concise and natural for better results.
* Use punctuation to control pauses and emphasis.
* Avoid unusual punctuations / symbols.
* Test with different voices to find the one that fits your project tone.
## 🙋♂️FAQs
**"Can I preview the voice before generating?"** --> Yes, use the play button next to the voice type selector to hear a sample. Hint: If you enter some text before clicking the play button, your text will be used instead of a standard example!
**"How many characters can I use?"** --> The character count and remaining credits are shown at the top of the panel.
**"Can I generate speech in other languages?"** --> Yes, simply select the language from the list and type your text in that language.
# Add zooms
## ❓ What is it?
Videos made with a single-camera setup can seem boring and monotonous. Adding zoom-in at key moments in the video is a popular way of adding some motion to this setup.
This FireCut feature uses AI to figure out these key moments in your video, and adds zooms automatically on a new video track using [Adjustment Layers](https://www.softwarehow.com/add-adjustment-layer-adobe-premiere-pro/).
## 🤔 How does it work?
This feature works by:
* Breaking your sequence (or the selected scope if using in/out points) into smaller chunks for processing, typically 1 minute each
* Analysing these chunks one at a time for key moments based on what is being spoken
* For each chunk, adding one or more zoom-in Adjustment Layer clips
{% embed url="" %}
## ⚙️ Settings
There are a number of settings for adding zooms:
1. **Zoom frequency:** This lets you decide how often FireCut should add a zoom. You can pick a value you're comfortable with in this scale
* **Low frequency** is for slow-paced (typically long-form) content, and will add \~1 zoom per minute of video
* The middle (default) setting will add \~2 to 4 zooms per minute of video
* **High frequency** is for fast-paced (typically short-form) content, and will add \~7 zooms per minute of video
2. **Zoom style:** What the zooms look and feel like...
* **Scale:** How far in to zoom. This works exactly like the Scale property on any video, where 100 is 1x size (or no scaling), and 200 is 2x size. **A good starting point is 120**
* **Center point:** Pick where in the frame to zoom in to. The default is the center of the frame, but you might want to adjust it if you want to specifically zoom in to speaker's face.
* **Animated:** Whether to gradually zoom in with an animation (Animated = selected), or add a sharp zoom cut wihout an animation (Animated = unselected). If animated, this applies keyframes to the Adjustment Layers that are added
* **Animation duration:** If "Animated" is selected, this controls the duration of the animation. You should try it out to find the best value. **A good starting point is 0.2 to 0.5 sec**
*
3. **Animation:** Whether to gradually zoom in with an animation (Animated = selected), or add a sharp zoom cut wihout an animation (Animated = unselected). If animated, this applies keyframes to the Adjustment Layers that are added
* **Duration:** This controls the duration of the animation. You should try it out to find the best value. **A good starting point is 0.8 sec**
* **Easing function:** This controls the easing / timing function for applying the zoom. The left-most option is a linear curve, which means your zoom will increase at a constant rate over the zoom duration you select. The right-most option has the smoothest ramp. **A good starting point is the middle option.**
4. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
5. **Language:** We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because [training sets for AI tend to be in English](https://www.wired.com/story/chatgpt-non-english-languages-ai-revolution/). On occasion, this might cause the operation to fail -- please do let us know () if this happens, so we can improve it for you!
## 💡 Tips for best outcomes
* **Try your settings on a small portion of your sequence** before processing hours of footage
* **Be mindful of usage**, as this feature counts towards your AI quota
* **Remove any repetitions** / multiple takes in your video first
* **Ensure your audio is clear and loud**
* **Mute any tracks with music** / sound effects that might obscure the sound of the speaker
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"I can't see the zoom clips / Adjustment Layers"** --> These are always added to a new video track at the top of your sequence - this can often be hidden at the top of your sequence, so try scrolling up to make sure it's not hiding from you!
* **"It didn't work on my non-English video"** --> Please drop a note at . We are keen to make sure this feature works reliably on all supported languages!
* **"The zooms were not placed at sensible points"** --> Make sure you have a clear, single speaker in the audio so that your script can be picked up and analysed. If there are any sound effects, multiple speakers, music, noise, etc., this can throw off the analysis in some occasions
# Add captions
## ❓ What is it?
FireCut lets you add captions to your video.
While English is fully supported, **FireCut also lets you transcribe audio in 50+ languages**; however, please do double-check the results because this is an experimental feature.
## 🤔 How does it work?
The "Add captions" feature:
* Transcribes your audio in 2 steps - **both are done automatically**
* (1) Sentence-level (takes \~5s per min of audio) -- gives a preview of the transcript
* (2) Word-level (takes \~5s per min of audio) -- gets accurate timings for transcript
* Lets you modify the captions in 2 different modes:
* **Styled captions** (if you want captions that are styled and animated within FireCut), or
* **Text-only captions** (if you just want a captions track that you can style yourself in Premiere)
* You can also export the captions as SRT or VTT files
{% embed url="" %}
### 1️⃣ Styled captions mode
* **When to use:** To easily get animated captions that match popular creators' styles
* **Output:** Caption images (.PNG files) inserted in a new video track in your sequence. Even though these are images, [**they can still be edited by FireCut**](#editing-styled-captions)
### 2️⃣ Text-only mode
* **When to use:** To get a text-only captions track that you can edit in Premiere
* **Output:** New captions track (requires PPro 2022+) that contains your transcript
## 💾 Saving your brand style
Once you have changed the various settings (e.g. font, text position, animation) to match your style, just **click one of the \[+] buttons** to save this style as a Preset. Next time, you can just click the name of the Preset to load the style again.
## :handshake: Sharing your style/preset with others
Once you have saved your style as a preset using the instructions above, you can also share it with other FireCut users. By default, these are shared with the FireCut community (i.e. they are available to all FireCut users), but if you are part of a Team plan you can choose to share it only with other members of your plan.
To share a preset:
* Click on "**Edit**" to see your list of custom presets\
* Click on the "**Share**" icon next to the preset you want to share
* Enter the preset's name, and your own name as you'd like it to be visible to other users, and (if you're on a Team plan), select a visibility scope - then hit "**Publish**"\
## ✏️ Editing styled captions
Styled captions are inserted as .PNG images in your sequence. This is done by design to give you a great deal of flexibility in how the captions are styled and animated.
While these are .PNG images, **it is still possible to edit them using FireCut.**
Just select the caption clips in the timeline, then **FireCut** > **Add captions** > **Edit selected caption.** This works for both nested caption clips and for individual caption clips.
This opens up the selected portion of your transcript in FireCut, allowing you to make any changes (e.g. changing the text or style). If you want to reload the full transcript instead of just the selected captions, click the "**Load full transcript**" button
To add the edited captions, just click "**Add styled captions to sequence**" once you're done.
## ⚙️ Settings
1. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
2. **Audio language:** We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because [training sets for AI tend to be in English](https://www.wired.com/story/chatgpt-non-english-languages-ai-revolution/). On occasion, this might cause the operation to fail -- please do let us know () if this happens, so we can improve it for you!
3. **Guidance prompt:** This textbox lets you provide a writing style to the transcription model in order to guide the transcript to be more in line with what you want. You can include things like:
1. **Brand names / Proper nouns** that may not be spelled correctly by default (e.g. type "FireCut" in order to correct "fire cut" to "FireCut" in the transcript)
2. **Capitalisation preference**, for example, if the transcript is coming out in lower case ("the park is green") and you want to force sentence case ("The park is green."), you can write a short sentence here in your preferred capitalisation and FireCut will try to follow that guidance
3. **Punctuation preference**, for example, if the transcript tends to miss punctuations, you can write a short sentence here with the preferred level of punctuation and the transcription will follow your guidance
4. **Translate to another language:** This setting lets you translate your captions to a different language. Be sure to set the audio language correctly to the language your original audio is in
5. **Use voice activity detection:** If you have long silences in your transcript, this can cause problems in the resulting transcript, such as repetitions of the same word or the model adding unrecognised words. Using voice activity detection (VAD) can help to eliminate this problem
## 💡 Tips for best outcomes
* **Make sure your audio does not have long silences**, and any music / sound effects are muted
* **Remove any repetitions first**, as FireCut might not transcribe multiple instances of the same text
* **Feel free to work in the timeline**, while FireCut is processing your audio -- however, changing the timing of your clips might cause the transcription to be misaligned (FireCut's transcription follows your **sequence**'s timecode, not individual clips)
## 🙋♂️ Common questions, issues, watch-outs
* **"The transcribed text was wrong"** -->
* **All languages:** Please make sure the audio is clear, there are no long silences, and no repetitions. If this doesn't fix the issue, please share your audio with us at
* **Non-English:** Transcription for non-English audio is currently experimental and expected to be 70-80% correct in most cases. If you're experiencing a much worse outcome, please get in touch and share your audio with us at
* **"The transcript has a style I don't like" (e.g. too many capital letters, everything in lowercase, missing punctuation, etc.)** -->
* Use the "guidance prompt" setting (see [#settings](#settings "mention") above) to guide the transcript's style
# Add titles
### ❓ What is it?
Adding animated text to your videos is a great way to keep viewers engaged and emphasize key points. The **Add titles** feature automatically identifies important phrases in your speech and turns them into highly customizable, animated text titles.
### 🤔 How does it work?
The "Add titles" feature works by analysing your speech and finding suggested titles directly onto your video.
* First, you choose a default theme for your titles and hit "Go" to start the analysis (Hint: You can hover over the themes to see their animations).
* FireCut will analyse your speech and automatically highlight phrases that would make great animated titles.
* You are then presented with a list of titles overlaid over your transcript where you can review, resize, and edit the titles before adding them onto your sequence.
* Alternatively, you can use **Manual mode** to bypass the automatic analysis and individually add titles at any specific point in your video.
{% embed url="" %}
### ⚙️ Settings
1. **Theme:** Decide how your titles will look when generated. You can also modify the theme later.
2. **Scope:** Whether to analyze your full sequence, or just in/out points.
### ✏️ Transcript and title editor
Once the analysis is complete, you can use the transcript editor to fine-tune your titles.
#### **To edit which words from your transcript are used for titles:**
* Turn on the "Edit mode" button in the Transcript section so it is green\
* Make changes in the transcript editor following the instructions under "Transcript" — you can make various changes such as changing which words are highlighted, changing emphasis levels for words, or even splitting/deleting titles by using the right-click context menu
#### **To edit specific titles:**
* Turn off the "Edit mode" button in the Transcript section so it is gray\
* Select the title you want to edit by either hovering on it in the transcript, or using the right/left arrow buttons to cycle through the titles\
* Use the title editor window to make changes — you can change the text, appearance and animation
### 💡 Tips for best outcomes
* **Confirm the visuals of the titles** before adding them to your sequence to save time on the edit.
* Use In/Out points (hotkeys: I and O) to limit analysis to the most relevant part of your video.
* **Make sure your audio does not have long silences**, and any music / sound effects are muted.
### 🙋♂️ Common questions, issues, watch-outs
This is a brand new beta feature that we're trying out! Please share your feedback.
# Find B-roll
## ❓ What is it?
FireCut can automatically find stock footage to use in your video based on its content.
## 🤔 How does it work?
The "Find B-rolls" feature:
* Transcribes your video
* Determines the best search terms for finding stock footage, based on the content of your video
* Searches your chosen stock footage library, and downloads and inserts these automatically
* Lets you review the chosen clips and swap them out with alternatives
{% embed url="" %}
## ⚙️ Settings
There are 6 main settings:
1. **B-roll frequency:** Similar to the frequency in the "Add zooms" feature, this lets you decide how often you want a B-roll clip to be placed in your sequence. The default is to add a new clip every 10 seconds.
2. **Method:** As this is a new feature, we are experimenting with different methods for finding the best stock footage. If you are unsure of what the options mean, just go with the default setting here.
3. **Library:** Which stock footage library to use.
4. **Match sequence orientation:** Selecting this option will force FireCut to only search for stock footage that matches your sequence's orientation, i.e. if you are making a short-form video in vertical orientation, it will only look for vertical stock footage, so that you don't end up stretching a horizontal clip to fit your sequence. Please note that this will reduce the variety of clips.
5. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys).
6. **Save location:** Where on your device to save your downloaded B-roll footage.
## ⬆️ Removing watermarks
When you first download B-roll videos from Storyblocks, these videos might have watermarks on them. This allows the feature to run significantly faster (because the videos are low-res) and allows your timeline to work more efficiently. It's like using a proxy when editing videos that are large in size.
When you've reviewed the results of the Find B-roll feature and want to download full-res versions without watermarks, just click on "**Upgrade B-rolls**" (this can be found in the Find B-roll menu; if you do not see it, just go back to the main menu and enter the Find B-roll menu while having at least one watermarked B-roll video in your timeline) and FireCut will get the full resolution versions for you.
## 💡 Tips for best outcomes
* **Make sure your audio does not have long silences**, and any music / sound effects are muted
* **Remove any repetitions first**, as FireCut might not transcribe multiple instances of the same text
* **Feel free to work in the timeline**, while FireCut is processing your audio -- however, changing the timing of your clips might cause the transcription to be misaligned (FireCut's transcription follows your **sequence**'s timecode, not individual clips)
## 🙋♂️ Common questions, issues, watch-outs
* **"The stock footage was not relevant to the video"** -->
* Please fill in the survey that opens after you run this feature. It is still a beta feature and needs your feedback in order to improve
# Find music
## ❓ What is it?
FireCut can automatically suggest and insert background music for your video — tailored to the mood, genre, and content of your sequence.
You can also manage which YouTube channels are whitelisted for music usage in your projects, ensuring you have the right permissions and access to music tracks.
## 🤔 How does it work?
The **Find Music** feature has **two modes**: *Automatic* and *Manual*.
#### 🎛️ Automatic Mode
* FireCut transcribes your selected sequence (either **Full Sequence** or your **In/Out Scope**)
* It analyzes the **genre and mood** of your clip
* Based on that, it recommends music tracks that best match your video
* You choose which **audio track** the music should be added to
* Music results appear below—you can **preview** each track and **insert** it into your timeline with one click
#### 🎚️ Manual Mode
Prefer more control? Use Manual Mode to:
* **Select a Genre** (e.g. cinematic, lo-fi, corporate, ambient)
* **Select a Mood** (e.g. uplifting, tense, emotional, mysterious)
* Get a curated set of music options based on your preferences
* Preview and insert just like in Automatic Mode
{% embed url="" %}
## 📋 YouTube Whitelisting
If you're using music for YouTube content, you can manage your whitelisted YouTube channels:
* **Add YouTube Channels**: Enter a YouTube Channel ID (usually starts with 'UC' followed by alphanumeric characters) to whitelist it for music usage - full instructions provided in the plugin.
* **View Whitelisted Channels**: See all currently whitelisted YouTube channels for your account
* **Channel Management**: Keep track of which channels have been whitelisted and when they were added
This ensures you have the proper permissions and licensing for using music tracks in your YouTube videos, and you don't get copyright strikes from the music rights owner.
## 💡 Tips for best outcomes
* Use In/Out points (hotkeys: I and O) to limit analysis to the most relevant part of your video
* If you're using voiceover, make sure it's clear. FireCut uses it to understand tone
* When whitelisting YouTube channels, make sure you have the correct Channel ID (not the channel name or URL). Channel IDs typically start with 'UC' and are found in your YouTube channel settings
## 🙋♂️FAQs
* **"The music didn't match the tone"** → Try Manual Mode and explore different genre/mood combos
* **"Too few options"** → We're expanding our music catalog weekly. You can also request styles via the in-app survey
* **"How do I find my YouTube Channel ID?"** → Go to your YouTube channel settings, or check the help tooltip in the whitelist management section for step-by-step instructions
* **"Can I whitelist multiple channels?"** → Yes! You can add multiple YouTube channels to your whitelist for different projects or channels
* **"What if I enter an invalid Channel ID?"** → FireCut will validate the format and show an error message if the Channel ID is invalid. Make sure it starts with 'UC' and contains only alphanumeric characters, hyphens, and underscores
# Detect chapters
## ❓ What is it?
Dividing your timeline into chapters can be very helpful.
When you're close to a final cut, chapter detection can give you markers that you can export as timestamps for YouTube (so YouTube can mark them as chapters in the video), and can even generate pretty motion graphics clips you can show at the start of each chapter.
You can also use it early in the process to put markers on your timeline (e.g. to mark things like "Introduction", "Topic 1, 2, 3, ...", "Sponsor segment", "Conclusion") for reference while you edit your video, making the project easier to navigate. These are just like any other markers and can be moved around and edited. **However, this is not the recommended use case at the moment,** because analysing a long sequence (>20 mins) can take quite a while with current technology.
{% hint style="success" %}
**Tip:** Analyzing a long sequence (>20 mins) can take a while with current technology. We suggest to run this feature close to the end of your editing process, after removing silences and repetitions.
{% endhint %}
## 🤔 How does it work?
Chapter detection in FireCut:
* Analyses the words being spoken in the selected portion of your sequence to detect when new topics are starting
* Shows these topics as timestamps in a list you can review and edit; you can add more topics, change the names of topics, and delete topics you don't want
* Lets you do 3 actions with this finalised list:
1. **Copy** your chapter timestamps as a text snippet to clipboard, for pasting into your YouTube video's description
2. Put these timestamps as **markers** in your timeline
3. Generate divider motion graphics **clips** that show an animated title; these are added to a new video track at the top of your sequence
{% embed url="" %}
## ⚙️ Settings
There are two main settings for chapter detection:
1. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
2. **Language:** We are constantly adding support for new languages. However, please note this is experimental and may create unpredictable results when compared with English. This is the case for every AI tool even if they don't mention it, because [training sets for AI tend to be in English](https://www.wired.com/story/chatgpt-non-english-languages-ai-revolution/). On occasion, this might cause the operation to fail -- please do let us know () if this happens, so we can improve it for you!
## 💡 Tips for best outcomes
* **Use towards the end of your workflow** so that your sequence is fairly short (<20 min)
* **Make sure your audio is loud and clear**, with any music / sound effects muted
* **Try it on a short section of your timeline first** to get familiar with the tool; processing larger sequences can take a while (\~2 min for every \~10 min of sequence)
* **You can edit the generated motion graphics clips** after they are placed in the timeline, e.g. changing the font size and text
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"I can't see the motion graphics clips"** --> These are always added to a new video track at the top of your sequence - this can often be hidden at the top of your sequence, so try scrolling up to make sure it's not hiding from you!
* **"The chapter topics / timestamps don't match up with my video"** --> Make sure you have a clear speaker in the audio so that your script can be picked up and analysed. If there are any sound effects, multiple speakers, music, noise, etc., this can throw off the analysis in some occasions
* **"It didn't work on my non-English video"** --> Please drop a note at . We are keen to make sure this feature works reliably on all supported languages!
# Multi-track
## ❓ What is it?
In FireCut, **Multi-track** means to edit your video by considering multiple tracks **separately** (conversely, all other features will treat the audio in your timeline / selected tracks as one single mixed-down track).
It offers 2 main features:
1. **Multi-track video editing to edit podcast-style videos** automatically, by switching between multiple video tracks based on multiple audio tracks. FireCut will "follow" the loudest audio (similar to how video conferencing tools like Zoom and MS Teams will show the speaker on the screen), plus add some variations in the final cut to prevent monotony
2. **Multi-track audio muting to disable quiet audio in selected tracks to remove background noise**, by listening to each track separately. This is similar to the silence cutting feature, except it analyses each audio track separately (rather than a combined mix-down) and only disables / mutes clips rather than deleting them
{% embed url="" %}
## ➡ Go to ...
{% content-ref url="/pages/JPy1uQY5f8XucBx51Jnu" %}
[Multi-track video editing](/features/multi-track/multi-track-video-editing)
{% endcontent-ref %}
{% content-ref url="/pages/1OHTDDDDK0lMZZELH5U8" %}
[Multi-track audio muting](/features/multi-track/multi-track-audio-muting)
{% endcontent-ref %}
# Multi-track video editing
## ❓ What is it?
**Multi-track video editing lets you edit podcast-style videos** automatically, by switching between multiple video tracks based on multiple audio tracks.
FireCut will "follow" the loudest audio (similar to how video conferencing tools like Zoom and MS Teams will show the speaker on the screen), plus add some variations in the final cut to prevent monotony
## 🤔 How does it work?
Multi-track video editing in FireCut:
* Lets you identify which video tracks correspond to which audio tracks; you can label the audio tracks by speaker names but this is completely optional
* Listens to each audio track separately and decides which one to focus on at any given moment
* Picks the corresponding video track to show on-screen (if the same speaker appears in multiple video tracks, it will pick the video track that hasn't been shown in a while, to give some variation in your cuts)
* Shows you a results list, where you can preview the cuts that will be made. You can play around with the settings to change how often the cuts happen
* Finally, it cuts the video once you are happy with the preview
## ⚙️ Settings
Once your video has been analysed, multi-track video editing has the following options:
1. **Speaker switching frequency:** How "sensitive" to be when switching between speakers. Increase to switch more often (as soon as another speaker becomes louder than the current speaker), or decrease to switch less often.
2. **Cutaways:** Cutaways are intentional cuts to non-speakers made to keep your video interesting
* **Max shot duration:** This is the limit of how long FireCut should show any given clip. If we go over this threshold, FireCut will add a cutaway to one of the other video tracks to help keep viewers engaged
* **Cutaway shot duration:** Whenever there is a cutaway (determined using the max. cut duration above), this setting determines how long that cutaway should be
3. **Cutting operation:** What to do with the "inactive" video segments, i.e. the parts that are *not* shown on screen because a different speaker is speaking. You can decide to either **disable** them (keep them in the timeline but grey them out so Premiere Pro ignores them), or to **delete** them altogether.
## 💡 Tips for best outcomes
* **Ensure your different audio tracks are similar in loudness**; if one speaker is always louder than another, they will naturally be focused on more
* **You can make cuts in the audio even before analysis**; for example, if you know for sure that you want to focus on a certain speaker for minute 3 of the sequence, feel free to add a cut in the audio and disable the other speakers to make sure they are the loudest in that moment. This is completely optional, but give you greater control
* **Avoid noisy audio (garbage in, garbage out!)** because you don't want background noise to be confused with the speaker's voice (some noise is OK, but if it's roughly the same loudness as the speaker, then the analysis won't get you good results)
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"Does it work on non-English audio?"** --> Yes, at the moment this feature follows the audio loudness rather than the words being spoken, so language isn't a consideration
* **"It's slow"** --> Which part is slow? The first part (rendering and analyzing your audio) is determined by how quick your audio is to export and read – if it's slow, try working with a different audio format (such as MP3 audio instead of WAV) to see if that makes a difference. If this is the case, you can try to re-render your project with a different audio format by rendering out the tracks as MP3 and re-importing them. The second part (actually cutting the sequence after analyzing and adjusting settings) is determined by the number of clips in your sequence. If you have a large number of clips, then try to reduce this by nesting your clips within nested sequences.
# Multi-track audio muting
## ❓ What is it?
**Multi-track audio muting disables quiet audio in selected tracks to remove background noise**, by listening to each track separately.
This is similar to the silence cutting feature, except it analyses each audio track separately (rather than a combined mix-down) and only disables / mutes clips rather than deleting them
## 🤔 How does it work?
Multi-track audio muting:
* Analyses each selected audio track to identify "silences", similar to how the silence cutting feature does it
* For each audio track:
* Wherever there is a silence, it adds a cut at the start and end of the silence (with enough padding to make sure it doesn't cut off words)
* Disables the portion of the clip in the silence, which has the effect of muting the clip without removing it from the sequence (so you can re-enable it if you like)
## ⚙️ Settings
Multi-track audio muting has the following options:
1. **Threshold method:** This feature analyses each audio track separately, which means you can let FireCut detect the best threshold for each track automatically, or you can specify a threshold to use. Whenever your audio falls below this threshold, FireCut will treat it as a silence and mute it.
2. **Apply to audio tracks:** These are the audio tracks you want to mute quiet audio in. All other tracks will be ignored. Even though this feature is technically a "multi-track" feature, you are free to apply it to a single track if you just want to mute one track.
3. **Scope:** You can decide whether to run the operation on your **Full sequence** or only on a certain portion that you specify with **In / Out points** (you can place these in your sequence using the `I` and `O` hotkeys)
4. **Disable linked video tracks:** This option tells FireCut to check which video clips are linked to the audio tracks in scope. If selected, FireCut will disable **both** the audio and the video clips corresponding to a silence. You should typically not need this settings, but it's there if you wish to hide the video at silent portions (e.g. if you want to show an overlay such as a facecam only at loud moments in its corresponding linked audio)
5. **Cutting algorithm:** How FireCut performs the cuts (this does not affect *where* the cuts actually happen). Over time, we release newer and faster algorithms. Currently we offer the following for multi-track audio muting (the recommended algorithms for this are slightly different from silence cutting, because muting is not as expensive an operation for your device):
* **Original:** Most reliable but slow, best for **short sequences** (<30 mins scope)
* **Rapid:** Faster and fairly reliable, best for **longer sequences** (30+ mins scope)
## 💡 Tips for best outcomes
* **Avoid noisy audio (garbage in, garbage out!)** because you don't want background noise to be confused with the speaker's voice (some noise is OK, but if it's roughly the same loudness as the speaker, then the analysis won't get you good results)
* **Don't work in the timeline** while FireCut is working in the background
## 🙋♂️ Common questions, issues, watch-outs
* **"Will FireCut disable full audio clips or will it only mute quiet portions in clips?"** --> At the moment, this feature is designed to make cuts in your existing audio clips wherever there is silence and mute the newly-created portion of silent clip.
# Create highlights
## **❓ What is it?**
Create highlights finds the most engaging moments in your sequence and turns them into short, ready‑to‑share clips. Ideal for shorts, reels, teasers, and social cut‑downs.
## **🤔 How does it work?**
* FireCut analyzes your audio transcript to spot compelling, self‑contained moments.
* It adds red chapter markers named “FC Highlight” at the suggested start/end times.
* You can review, move, add or delete highlights, then generate new sequence(s).
* Optional: re‑frame to 9:16, add captions, find B‑roll, and auto‑generate descriptions.
{% embed url="" %}
## **⚙️ Settings**
* **Detection**
* **Number of highlights**: Approximate frequency per hour of footage (slider).
* **Highlight duration**: Minimum/maximum target length (5–120s).
* **Scope**: Full sequence or In/Out points (set I/O in your timeline).
* **Accuracy**: Enhanced accuracy of start/end times (slower, more precise).
* **Language**: Set the spoken language (non‑English currently experimental).
* **Edit highlights**
* **Highlights list**: Click to jump to a highlight; move the red markers to adjust; “X” to delete.
* **Add new**: Select a range with In/Out points → “+ Add new highlight”.
* **Overlap guard**: If highlights overlap, generation is **disabled**.
* **Create sequences**
* **Re‑frame to 9:16** (vertical)
* Premiere Pro Auto Reframe: Motion tracking speed (slower/default/faster).
* Custom re‑framing (Beta): Use viewboxes with face detection; fine‑tune framing.
* **Add captions**: Apply your FireCut captions style to each highlight.
* **Find B‑roll**: Auto‑suggest B‑roll for each highlight.
* **Generate descriptions**: Create text descriptions for social posts; copy/regenerate.
* **Create multiple sequences**: Make one sequence per highlight, or a single combined sequence.
* **Output**: Sequences go to the “Highlights” bin with clear names (e.g. highlight\_… or \ highlights (… )).
## **💡 Tips for best outcomes**
* **Use In/Out points** to focus detection on the most relevant section.
* **Pick a sensible duration range** (e.g., 15–60s) to get tighter, punchier clips.
* **Turn on Enhanced accuracy** to get better timing accuracy for the highlights.
* **For vertical export**, re‑frame to 9:16; use Auto Reframe for speed, Custom for control.
* **Creating multiple sequences** is great when you want **separate** exports per highlight.
## **🙋♂️ Common questions, issues, watch-outs**
* **“No highlights found” →**
* Try widening the duration range, using a longer scope, or enabling Enhanced accuracy. Ensure the audio is clear enough to transcribe.
* **“The ‘Create…’ button is disabled” →**
* Highlights are overlapping. Adjust or delete overlaps in the Edit view.
* **“The highlights start/end a bit off” →**
* Move the red chapter markers directly, or enable Enhanced accuracy for tighter timings.
* **“Vertical framing isn’t centered” →**
* Use Custom re‑framing (Beta) and adjust viewboxes; or try a different Auto Reframe speed.
* **“Descriptions didn’t appear” →**
* Click Regenerate or ensure you enabled Generate descriptions before creation.
# Workflows
### ❓ What is it?
**Workflows** allow you to create and run multi-step automations to speed up your editing process across multiple projects. By chaining multiple FireCut features together, you can create a "fire & forget" process that takes your video from raw footage to a polished cut in a single click.
For example, you can create a workflow that automatically runs "Remove silences", then "Remove repetition", then "Add B-roll", and finally "Add captions."
The following features are currently available to use as steps in a workflow (these utilize their "auto" variants to ensure a workflow runs smoothly without interruptions):
* Remove silences
* Remove repetition
* Add zooms
* Add B-roll
* Add captions
* Add chapters
* Remove profanity
* Find music
### 🤔 How does it work?
To access this feature, open the **Workflows** menu in FireCut. From here, you will see your list of existing workflows.
* To **run a workflow**, simply click on a workflow in the list to start it.
* To **create a new workflow:** click the "+" button on the top.
* To **edit a workflow**, click the "edit" button (pen icon) next to it.
* **Building a workflow:** Give your workflow a name and start adding steps. Every time you add a step, you will be taken to the specific settings menu for that feature so you can define exactly how it should behave.
* **Running a workflow:** Once started, FireCut will process your entire workflow step-by-step using the settings you chose. If a specific step doesn't find anything to do or encounters an issue (for example, if find B-roll finds no footage), the workflow will safely continue to the next step. The results of all the different steps will be shown at the end.
{% embed url="" %}
### ⚙️ Settings
When creating or editing a workflow, you configure the settings for each individual step right inside the workflow builder.
* Each step you add will allow you to set its specific settings (like silence thresholds, caption themes, or zoom frequency). These settings are saved to the workflow itself, allowing you to create highly tailored automations for the different types of footage you have.
### 💡 Tips for best outcomes
* Workflows are designed to process your **whole sequence**. In/Out points are ignored when running a workflow.
* Running large workflows with many steps on long videos may take a while to process. You should avoid making changes on the timeline while a workflow is in progress.
* The features inside a workflow act exactly as they act alone, so you can use your existing knowledge when customizing them. As always, you can also refer to the existing documentation for a feature if you need to.
### 🙋♂️ Common questions, issues, watch-outs
* **"Can I undo a workflow if I don't like the result?"** --> Yes! Just like any other action in FireCut, you can use the standard FireCut **Undo** button at the top of the plugin to roll back the entire workflow operation.
* **"Can I apply a workflow to just a small section of my timeline?"** --> Currently, workflows apply to the entire sequence and do not use In/Out points. If you only want to process a small clip, we recommend running the individual features manually or dropping that clip into a new sequence before running the workflow.
* **"What happens if a step fails or finds no results?"** --> The workflow will not fail completely. It will just continue to the next step, and will provide a summary of the results at the very end, whether successful or otherwise.
* **"Do you save checkpoints after every workflow step?"** --> Yes, FireCut saves a copy of your sequence after every workflow step. This is saved in your **Project -> FireCut -> Workflows** bin
# Script guidance
### ❓ What is it?
Script guidance turns a raw, unedited recording into a clean first cut that follows a written script.
If you record talking-head or "self-tape" style videos — reading from a script, doing several takes, stumbling over lines, and chatting between takes — you usually end up with a long clip full of retries and off-script moments. Script guidance reads your finished script, finds the parts of your footage that actually match it (in order), and builds a **new timeline that contains only those parts**.
You give FireCut two things:
* **One source video clip** (that already contains audio)
* **Your script**, as a plain-text `.txt` file
…and FireCut produces a new sequence with the off-script takes, slip-ups and retries removed.
> Script guidance is in beta and the transcription is experimental, so always review the result before relying on it.
{% embed url="" %}
### 🤔 How does it work?
The feature works in four stages. Stages 1–2 are automatic; stage 3 is where you review and fine-tune; stage 4 builds the cut.
#### 1️⃣ Transcribe your clip
Pick a video clip from your project tree (bins expand and collapse; only a single clip can be selected, not a bin), choose the **Audio language**, and click **Transcribe**.
* FireCut transcribes the **whole clip** using a transcription model (Scribe) chosen specifically because it handles raw footage well — repeated takes, false starts, and filler don't throw it off.
* Transcripts are **saved and reused**. If you've already transcribed a clip, the button reads **Load transcript** and the transcript opens instantly instead of being re-generated. Clips that already have a transcript show a captions icon in the tree. This means you can iterate on your script and settings as much as you like without ever re-transcribing.
* Maximum clip length is **30 minutes**.
#### 2️⃣ Map your script to the transcript
Provide your script in the **Script** panel (left). If it's empty, click **"Missing script → Click here to open a script"** to import a `.txt` file (up to 30,000 characters). FireCut then matches your script against the transcript and **color-codes the matched sections** across both panels — Script on the left, Video transcript on the right.
The matcher is deliberately tolerant so it survives real-world recordings:
* **Small misspeaks and transcription errors** still match (fuzzy matching at the word and phrase level).
* **Numbers and their words are treated as equal** — `2` matches "two", `21` matches "twenty-one".
* **Common symbols match their spoken form** — "and" ↔ `&`, "percent" ↔ `%`, "dollars" ↔ `$`, "at" ↔ `@`, "plus" ↔ `+`, and so on.
* **Off-script content is ignored.** Anything you said that isn't in the script — retries, "okay, let me do that again", ums — simply never gets claimed by a section, so it's left out of the final cut. Script lines you never actually said are skipped too.
* **Repeated lines** resolve to one occurrence. FireCut scans top-to-bottom and keeps the first good take of a repeated line (and, with *Align to sentences* on, snaps it to clean sentence edges).
#### 3️⃣ Review and edit the mapping
This panel is the heart of the feature — see **Reviewing & editing the mapping** below. Matched sections are color-coded; hovering a section highlights and scrolls to its counterpart in the other panel.
#### 4️⃣ Create the timeline
Click **Create timeline**. FireCut:
* Creates a **brand-new sequence** named **"FireCut Script - {your clip name}"** (in a *Script* sub-bin) built from your source clip. **Your original sequence is left completely untouched.**
* Keeps only the matched sections and **removes everything else** — the unmatched parts are cut out and the gaps closed (a ripple delete, the same mechanism as silence removal), not just muted or disabled.
* If your matched sections already cover the whole clip, it tells you *"Script timeline created (no cuts required)"* and still creates the sequence.
The result is your original clip reduced to just the parts that correspond to your script, in order — a starting point you can refine further in Premiere.
### ✏️ Reviewing & editing the mapping
Before you create the timeline, you have full manual control over what gets kept. Everything below lives on the results screen.
* **Edit the script** — the Script panel is directly editable. As you type, FireCut re-maps automatically. Use **Clear** to wipe the script and start over.
* **Adjust a selection** — hover over a colored section in the transcript and drag the chevron handles on its edges to grow or shrink what's included.
* **Add a section** — drag-select across un-highlighted transcript text to **force-keep** a portion that wasn't matched automatically (useful for an ad-lib you want to keep).
* **Delete a section** — right-click a section and choose **Delete section**.
* **Re-run mapping** — recompute the automatic mapping from scratch.
> **Heads up — manual edits "freeze" the mapping.** The moment you adjust, add, or delete a transcript selection, FireCut stops auto-remapping so it won't overwrite your work. The status changes from **"✓ Mapped"** to a yellow **"✎ Edited"**, and a **Re-run mapping** button appears. While frozen, editing the script text saves it but no longer remaps. Clicking **Re-run mapping** recomputes from the script and **discards your manual transcript edits** (you'll be asked to confirm: *"Re-running the mapping will discard your manual transcript edits. Continue?"*).
### ⚙️ Settings
#### Transcription
* **Source clip** — the single video clip to transcribe. Expand bins to find it; only clips (not bins) can be selected. One clip at a time.
* **Audio language** — set this to the language of your audio. This is an **experimental** setting and currently supports **left-to-right languages only** (right-to-left languages such as Arabic and Hebrew aren't available yet).
#### Mapping controls
Open these with the sliders icon next to **Mapping**. Changing any of them re-maps live (after a short pause), and each has a reset (↺) button.
* **Minimum match length** *(default 5; range 1–20)* — how many words in a row must agree before a chunk counts as a match. **Higher** → fewer, more confident matches. **Lower** → more (and shorter) matches, but more false positives.
* **Fuzzy matching word factor** *(default 50%; range 0–75%)* — how different two single words can be while still counting as the same word. **Higher** → more forgiving of mis-transcriptions. **Lower** → stricter.
* **Fuzzy matching phrase factor** *(default 20%; range 0–75%)* — when a single word fails to match, FireCut looks ahead and compares short phrases instead; this controls how different those phrases can be. **Higher** → bridges bigger gaps across errors.
* **Fuzzy matching phrase length** *(default 50; range 10–250)* — how many characters of look-ahead the phrase comparison uses.
* **Align to sentences** *(default on)* — snaps section boundaries to sentence endings where possible. Especially helpful around repeated lines.
#### Timeline controls
Open these with the sliders icon next to **Timeline**. These control the *cut*, and are applied when you click **Create timeline** (they don't change the on-screen mapping).
* **Section edge padding** *(default 0.6s; range 0.1–5s)* — extra time kept before and after each matched section so cuts have breathing room. **Higher** → looser cuts with more around each section. **Lower** → tighter cuts.
* **Remove pauses longer than** *(default 1.0s; range 0.1–5s)* — trims long silent gaps *inside* a kept section. **Lower** → tighter (removes shorter pauses too). **Higher** → keeps longer in-section pauses.
> Together, **Section edge padding** and **Remove pauses longer than** act as your "cut tightness" controls.
### 💡 Tips for best outcomes
* **Use clean audio.** Mute background music and sound effects, and keep speech clear — the cleaner the transcript, the better the matches.
* **Match your script to what you actually said.** The closer the script wording is to your spoken words, the more reliably it maps. If a take drifted from the script, either loosen the fuzzy settings or tweak the script/transcript text.
* **Keep your script in spoken order.** FireCut scans top-to-bottom and matches the first good occurrence within range, so large re-orderings can confuse it.
* **Iterate freely.** The transcript is saved after the first run, so adjusting your script and the mapping sliders never re-transcribes. Tweak, watch the highlights update, then create the timeline.
* **Fine-tune by hand when needed.** Drag the section handles or force-keep a selection rather than fighting the sliders for one stubborn section.
* **Treat the output as a first cut.** It's a fast starting point; do your final trims in Premiere.
### 🙋♂️ Common questions, issues, watch-outs
* **"A good take or line is missing from the cut"** → Loosen the matching: lower **Minimum match length**, or raise **Fuzzy matching word factor** / **phrase factor**. Also check that your script wording matches what you actually said. As a last resort, drag-select that part of the transcript to **force-keep** it.
* **"It kept the wrong take of a line I repeated"** → Drag the section's handles to move the selection, or **Delete section** and force-keep the take you want. Keeping **Align to sentences** on usually helps repeated lines snap to clean boundaries.
* **"The cuts feel too tight / words get clipped"** → Raise **Section edge padding**.
* **"Long pauses are left in the cut"** → Lower **Remove pauses longer than**.
* **"I edited the transcript and now editing the script does nothing"** → Manual transcript edits **freeze** the mapping so they aren't overwritten. Click **Re-run mapping** to return to automatic mapping — note this discards your manual transcript edits.
* **"My language isn't in the list"** → Script guidance currently supports left-to-right languages only. Right-to-left languages (Arabic, Hebrew, etc.) aren't supported yet.
* **"My clip is too long" / "I have multiple source clips"** → Clips are limited to **30 minutes**, and the feature works on **one clip at a time** — multiple or joined source media aren't supported yet.
* **"Will this change my original sequence?"** → No. Create timeline builds a **separate new sequence** ("FireCut Script - …"). Your original is untouched. The unmatched parts in the new sequence are removed (ripple-deleted), not just disabled.
* **"The transcript has mistakes"** → Because audio is transcribed automatically (and non-English is experimental), some errors are expected — fuzzy matching is designed to tolerate them. If the transcript is badly off, make sure the audio is clear and free of long silences; if it persists, share your audio with us at .
# Magic cut
### ❓ What is it?
Magic cut turns a raw, unedited talking-head recording into a finished first edit with one click.
If you record talking-head or "self-tape" style videos (several takes, false starts, stumbles, and chat between takes) you usually face lots of manual work before the video is watchable: cutting the bad takes, tightening pauses, adding captions, zooms and chapters.
**Magic cut does all of that in one pass.** It transcribes your footage, works out which parts are false starts, stutters and duplicate takes, removes them, and builds a brand-new sequence with editing extras (zooms, captions, titles, chapters) layered on automatically.
You give FireCut one thing:
* One source **video clip or sequence** (that already contains audio)
…and FireCut produces a new, fully assembled sequence. **1 click is all you need.**
{% embed url="" %}
### 🤔 How does it work?
The feature works in three stages, all automatic after you press **Go**.
#### 1️⃣ Transcribe your footage
**Pick a video clip or sequence from your project tree** (bins expand and collapse; a small icon shows whether each item is a video file or a sequence) and click **Go**.
If you've changed the source (e.g. you moved some things around in a sequence that was previously transcribed), **you can force a re-transcription**. Use the \[…] menu on the Go button → Re-transcribe and Go.
#### 2️⃣ Cut the timeline
**FireCut builds a new sequence containing only the kept parts:**
* Word timings are tightened against the actual audio waveform (using a silence threshold measured from *your* clip, so breaths and trailing sounds are trimmed accurately).
* Long silences *inside* a kept section are cut too.
* A subtle audio crossfade is added at every cut, so edits don't pop or click.
#### 3️⃣ Enhancements
**Magic cut then layers on enhancements.** Which ones depends on the video's format, detected from its shape and length. The extras include zooms, punch-out, captions, titles and chapters, depending on your input video/sequence. These are selected automatically.
Everything lands on its own track, so the result stays easy to edit; just disable the tracks you don't want.
### ✏️ Reviewing & editing the cuts
By default Magic cut applies its cuts immediately. If you'd like to approve them first, open **Advanced options** and turn on **Review cuts before applying**.
With review on, pressing Go runs the analysis and then pauses on a **Review cuts** panel showing your full transcript with shaded sections (to be kept):
* **Adjust a section** — hover a shaded section and drag the chevron handles on its edges to grow or shrink what's kept.
* **Add a section** — drag-select across un-shaded transcript text to force-keep something the AI cut (a take you liked, an ad-lib).
* **Delete a section** — right-click a shaded section and choose **Delete section**.
* **Create timeline** — build the sequence from your (edited) selection.
* **Cancel** — return to the Magic cut screen. Nothing is modified.
### ⚙️ Settings
#### Source
* **Source clip or sequence** — the single item to edit. Expand bins to find it; only clips and sequences (not bins) can be selected, one at a time. Items with a saved transcript show a captions badge.
* **Go** — runs the whole pipeline. If the selected item already has a transcript, the **\[…]** menu on the button offers **Re-transcribe and Go** to force a fresh transcription (this also clears the cached cut decisions).
#### Advanced options
* **Audio language** (default: Auto-detect) — the language of the spoken audio, used for transcription. Auto-detect lets the transcription model identify the language itself; set it explicitly if detection gets it wrong.
* **Review cuts before applying** (default: off) — pause after the analysis so you can approve, adjust or reject the proposed cuts before the timeline is built (see above). Off = the one-click flow.
### 💡 Tips for best outcomes
* **Use clean audio.** Mute background music and sound effects, and keep speech clear — the cleaner the transcript, the better the cut decisions.
* **Record with cuts in mind.** If you flub a line, just pause and start the line again — repeated takes are exactly what Magic cut is built to resolve. Long pauses between takes actually help, both for detection and for accurate trimming.
* **Iterate freely.** The transcript *and* the cut analysis are both cached, so re-running Magic cut on the same source is fast and consistent — experiment with review mode without waiting.
* **Treat the output as a strong first cut.** It's designed to be edited: every enhancement is a normal clip on its own track, so you can tweak or remove any piece in Premiere.
### 🙋♂️ Common questions, issues, watch-outs
* **"It cut a take I wanted" / "It kept the wrong take"** → Turn on *Review cuts before applying* and re-run — the analysis is cached, so it's quick. In the review panel, drag-select to force-keep the take you want, or delete/resize sections before building.
* **"The transcription language is wrong"** → Set **Advanced options → Audio language** explicitly, then use **\[…] → Re-transcribe and Go** so the clip is transcribed again in that language (the saved transcript is reused otherwise).
* **"Why didn't I get captions/titles?"** → Captions and titles are part of the *shortform* treatment.
* **"A title covers words that are missing from the captions"** → That's intentional: the caption clips underneath each title are disabled, not deleted. To reject a title, delete the title clip on V5 and re-enable the disabled caption clips on V4.
* **"Will this change my original clip or sequence?"** → No. Magic cut builds a separate new sequence ("FireCut Magic - …"). The source is untouched.
* **"I ran it twice and got the same cut"** → The cut analysis is cached per source so results are consistent (and fast). Use **\[…] → Re-transcribe and Go** to start completely fresh.
* **"Can I run it on multiple clips at once?"** → Not yet — Magic cut works on one clip or sequence at a time. To edit a multi-clip shoot, assemble the clips into a sequence first and select that sequence as the source.
* **"There's an extra copy of my source clip in the FireCut bin"** → That's a side effect of how Premiere imports the assembled sequence; it's a reference to the same media file (not a duplicate on disk) and the new sequence depends on it, so leave it in place.
* **"The transcript has mistakes"** → Because audio is transcribed automatically, some errors are expected, and the cut analysis is built to tolerate them. If results are badly off, check the audio is clean and the language is right; if it persists, share your audio with us at .
# Plans
We currently offer both Individual and Team plans. Please see the details [here](https://firecut.ai/pricing).