What is FunClip used for?

FunClip is an open-source, locally deployed video clipping tool that uses FunASR Paraformer models for speech recognition and allows users to select text segments or speakers to clip videos. It is a good fit for clipping video segments based on transcribed text or speaker identity, generating subtitles for videos and creating video clips from Chinese-language videos.

Is FunClip open source?

Yes. FunClip is open source under the MIT licence. Its source code is on GitHub at modelscope/FunClip and is written mainly in Python.

Yes. FunClip is open source, so the software itself is free to use.

Can I self-host FunClip?

Yes. FunClip can be self-hosted on your own server or infrastructure.

What is FunClip an alternative to?

FunClip is an open-source alternative to Opus Clip. Other open-source alternatives to Opus Clip include AI YouTube Shorts Generator, AutoClip and SupoClip.

Is FunClip actively maintained?

Yes. The most recent commit to FunClip was on 8 October 2026, and the latest release is v2.2.1, published on 1 September 2026. The project has 6.4k stars on GitHub.

FunClip: open-source alternative to Opus Clip

About FunClip

FunClip is a fully open-source, locally deployed automated video clipping tool. It uses Alibaba TONGYI speech lab's open-source FunASR Paraformer series models to perform speech recognition on videos, with integrated timestamp prediction.

Users can choose text segments or speakers from the recognition results and click the clip button to obtain the corresponding video clip. The tool supports multi-segment free clipping and automatically returns full video SRT subtitles and target segment SRT subtitles. It is realized through Gradio interaction and can be deployed on a server and accessed via a browser.

Key features

Integrates Paraformer-Large, an open-source Chinese ASR model with over 13 million downloads on Modelscope
Includes hotword customization via SeACo-Paraformer to enhance recognition of specified entity words or names
Integrates CAM++ speaker recognition model for clipping segments from a specific speaker
Supports multi-segment free clipping and returns full video SRT subtitles and target segment SRT subtitles
Offers LLM-based AI clipping functionality
Can be deployed on a server and accessed via a browser

Good fit for

Clipping video segments based on transcribed text or speaker identity
Generating subtitles for videos
Creating video clips from Chinese-language videos

Built with: Python tools
Tags: video-clipping; asr; subtitles; gradio; funasr; llm

FunClip: questions and answers

What is FunClip used for?: FunClip is an open-source, locally deployed video clipping tool that uses FunASR Paraformer models for speech recognition and allows users to select text segments or speakers to clip videos. It is a good fit for clipping video segments based on transcribed text or speaker identity, generating subtitles for videos and creating video clips from Chinese-language videos.
Is FunClip open source?: Yes. FunClip is open source under the MIT licence. Its source code is on GitHub at modelscope/FunClip and is written mainly in Python.
Is FunClip free?: Yes. FunClip is open source, so the software itself is free to use.
Can I self-host FunClip?: Yes. FunClip can be self-hosted on your own server or infrastructure.
What is FunClip an alternative to?: FunClip is an open-source alternative to Opus Clip. Other open-source alternatives to Opus Clip include AI YouTube Shorts Generator, AutoClip and SupoClip.
Is FunClip actively maintained?: Yes. The most recent commit to FunClip was on 8 October 2026, and the latest release is v2.2.1, published on 1 September 2026. The project has 6.4k stars on GitHub.