whatisgithub

What is funclip?

modelscope/funclip — explained in plain English

Analysis updated 2026-06-26

5,599PythonAudience · generalComplexity · 2/5Setup · moderate

In one sentence

A locally-run Python tool that transcribes speech in a video file and lets you cut out specific clips by selecting lines from the transcript, with optional AI-assisted clip selection using a language model to find the most interesting moments.

Mindmap

mindmap
  root((funclip))
    Core workflow
      Upload video
      Auto transcribe speech
      Select transcript lines
      Export clip
    Speech features
      Chinese audio strength
      Speaker identification
      Custom vocabulary
    AI clip selection
      LLM picks highlights
      Qwen and GPT supported
    Output options
      Video clip export
      Burned-in subtitles
      SRT subtitle files
    Interfaces
      Gradio browser UI
      Command line
      Hosted demo online
Click or tap to explore — scroll the page freely

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Transcribe a long recorded meeting and export individual clips for each agenda topic based on what was spoken, without manually scrubbing the video.

USE CASE 2

Cut highlight clips from a Chinese-language interview by searching the transcript for specific spoken phrases and exporting just those segments.

USE CASE 3

Let an AI language model automatically identify and extract the most interesting moments from a podcast recording without reading through the full transcript yourself.

USE CASE 4

Burn subtitles into a clipped video segment and export an SRT file ready to import into a video editor.

What is it built with?

PythonGradioFFmpegImageMagick

How does it compare?

modelscope/funcliphuggingface/alignment-handbookvibora-io/vibora
Stars5,5995,5985,598
LanguagePythonPythonPython
Setup difficultymoderatehardeasy
Complexity2/55/53/5
Audiencegeneralresearcherdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 30min

Requires Python plus FFmpeg and ImageMagick for subtitle burning, GPU optional but speeds up transcription.

So what is it?

FunClip is a free, locally-run tool that automatically transcribes speech in a video file and then lets you cut out specific clips based on the transcript. The idea is simple: instead of manually scrubbing through a video to find a specific moment, you search the spoken words, select the sentences you want, and the tool cuts out that segment of the video for you. The transcription step uses speech recognition models developed by Alibaba's research lab, which are particularly strong at Chinese audio. The tool also does speaker identification, so if a video has multiple people talking, you can ask for all the moments where a specific person spoke and clip those out together. Custom vocabulary can be added to improve recognition accuracy for names, brand terms, or technical jargon. A newer feature connects the tool to large language models such as Alibaba's Qwen or OpenAI's GPT. After the transcript is generated, you can prompt one of these models to identify which parts of the video are most interesting or relevant to a topic, and FunClip will then clip those sections automatically. The idea is to let AI decide what to cut rather than reading through the full transcript yourself. The interface runs as a local web page powered by Gradio, a library that turns Python scripts into browser-based forms. You upload a video, wait for transcription, copy the text you want, and click a button to get the clip. The tool can also burn subtitles into the clipped video, and it exports SRT subtitle files for the full video and for each selected segment. Installation requires Python and a few packages. Optional features for embedded subtitles also need FFmpeg and ImageMagick. The tool can be used through the browser interface, on the command line, or tried online without any installation via hosted versions on Modelscope and HuggingFace.

Copy-paste prompts

Prompt 1
Help me run FunClip locally to transcribe a one-hour meeting recording and export a separate clip for each agenda item based on the spoken timestamps in the transcript.
Prompt 2
I have a Chinese-language interview video with two speakers. Show me how to use FunClip's speaker identification feature to find and clip every moment one specific speaker talks.
Prompt 3
Help me write a Python script that uses FunClip's command-line interface to batch-process a folder of podcast MP4 files, using the LLM selection feature to extract the top three most engaging moments from each one.
Prompt 4
Show me how to install FunClip on a machine with Python, including the optional FFmpeg and ImageMagick dependencies needed for burned-in subtitle export.

Frequently asked questions

What is funclip?

A locally-run Python tool that transcribes speech in a video file and lets you cut out specific clips by selecting lines from the transcript, with optional AI-assisted clip selection using a language model to find the most interesting moments.

What language is funclip written in?

Mainly Python. The stack also includes Python, Gradio, FFmpeg.

How hard is funclip to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is funclip for?

Mainly general.

Open on GitHub → Ask about another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.