OpenChatCut
Lets you edit videos by chatting with an AI, then fine-tune the cuts on a real timeline
by sline
FunClip
by ModelScopeAppMake video or audio
Transcribes a video, then cuts out the parts you pick from the text, with subtitles
The problem it solves
You have a one-hour talk and need a two-minute clip of one answer, but finding it means scrubbing back and forth through the timeline.
For Video editorsPeople who share talks and interviewsTeachers and course makers
- Before
- You watch the whole recording, note timestamps by hand and cut each piece in a video editor.
- After
- You read the transcript, copy the sentences or speaker you want and get a clip with subtitles in a few clicks.
- Stars
- ★ 6.5k
- License
- MIT
- Cost
- Free
- Platforms
- Web · Mac · Win · Linux
- Runs
- Cloud · Local
Overview
FunClip is an open-source video clipping tool built on the open FunASR speech models from Alibaba's Tongyi speech lab. You upload a video, it writes out what is said with timestamps and can tell speakers apart, and you copy the sentences or speaker you want to keep. It then cuts those parts into a new clip, with subtitles if you ask, and can also let a language model suggest the highlights. You can try it on an official web page or run it on your own computer. It suits people who edit talks, interviews and lectures, especially in Chinese.
You edit the video by choosing sentences in a transcript instead of scrubbing a timeline, and the speech recognition runs on open models.
Try these first
Start with the first one: it is a small task you can check easily.
- On the web version, run recognition on a demo video, copy one sentence into Text to Clip and click Clip.First try · uploads your video
- Turn on speaker recognition for [interview video] and clip only what speaker 1 says.uploads your video
- Clip these two sentences from [lecture video] and add white subtitles.uploads your video
- Ask the language model to pick up to four highlights from the subtitles, then click AI Clip.needs an API key
Example prompts written by Agent Flows Hub.
Features
From the creator's documentation.
| Feature | What it does | Runs |
|---|---|---|
| Transcription | Full text of the speech with timestamps and an SRT subtitle file | Your video |
| Text-based clipping | Cuts out the sentences you copy from the transcript, with optional start and end padding | Your video |
| Speaker clipping | Tells speakers apart and clips everything one speaker says | Your video |
| Subtitles on clips | Burns subtitles into the clip in the font size and colour you pick | Your video |
| Hotwords | A list of names or terms to help recognition get them right (Chinese only) | Your video |
| AI highlights | A language model suggests clip ranges from the subtitles; needs that service's API key | LLM service |
Good to know
Cut highlight clips from a recorded talk or interview. FunClip transcribes the video, lets you choose the sentences or the speaker you want and exports those parts as a clip with matching subtitles.
Limits
- The default speech model is for Mandarin; English audio needs the English option when you run it yourself, and accuracy depends on the model you choose.
- Running it locally needs a Python setup and separate model downloads. AI-suggested clips send the transcript to the language model service whose key you enter.
Notes by Agent Flows Hub (original project name: FunClip), written from the creator's documentation, not from running it ourselves. FunClip README · FunClip on Hugging Face Spaces
Stuck setting it up?
Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.
More to make video or audio
Other apps
- Gamma Turns a topic, notes or a document into a designed presentation, document or web page
- Gemini Notebook Answers questions about your own documents and turns them into audio and study aids
- GenOffice Opens Word, Excel and PowerPoint files and lets an AI edit them, with changes you can undo
- go-stock Tracks Chinese, Hong Kong and US stocks and lets an AI model summarise news and charts
- Google AI Edge Gallery Runs AI chat, photo questions and transcription on your phone, with no internet needed
- Granola Turns your rough meeting notes and the call audio into clear notes and action items