No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Worth a lookEstablished, with a few things to check (listed below).
Check this first: Strongest results are for Chinese speech; English support is less emphasised.
Things to check
- Strongest results are for Chinese speech; English support is less emphasised
- Model weights are downloaded separately on first start and can be large
- LLM clipping needs an API key for an external language model service, which may cost money
- Dependencies are version-sensitive (Transformers 4.x, Gradio 4, funasr 1.4.9 or later)
Can you use FunClip commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with FunClip?
- Transcribe a video and cut clips by selecting the text or speaker you want
- Generate SRT subtitles for a full video or just the chosen clips and burn them in
- Ask a language model to suggest which parts of a recording to clip
How do you get FunClip running?
Clone the repository, create a Python 3.12 virtual environment, install requirements with pip (with a matching PyTorch), then run python funclip/launch.py to start the web interface.
Follow the official instructions in the project README.
Make money with it
A freelancer could offer a clip-and-subtitle service, turning clients' long recordings into short captioned videos for social media.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Cut short social media clips from webinars, interviews or podcasts without paying for a subscription editor
- Produce subtitle files for client videos in-house instead of paying for a transcription service
Checked 06 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.