voice-ai

FunClip: Turn Videos into searchable subtitles and clips fast

Name: FunClip: Turn Videos into searchable subtitles and clips fast
Author: modelscope

Founders can instantly transcribe, auto‑subtitle, and generate LLM‑guided video clips via a local Gradio UI—ideal for content teams needing rapid, accurate video assets. 6.4k+ GitHub stars.

From the repo · “FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.”

6,438 stars+45★ this week764 forksPythonGuide quality 8/10 · reviewed Oct 9Updated 10/8/2026100% free · open source

What it does

FunClip transcribes videos, generates subtitles, and clips them using AI, all through a simple, local interface.

When to use it

•You need to automatically generate subtitles for a large number of video files.
•You want to clip specific segments from videos based on spoken content.
•You require a tool that can handle video transcription and editing tasks without relying on cloud services.

Ready-to-paste prompt

python app.py --video_path=/path/to/example.mp4 --output_path=/path/to/output

Heads up: Ensure you have the necessary dependencies installed and the correct Python version, as FunClip requires specific versions of libraries like gradio and transformers to function properly.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/funclip && curl -fsSL https://workflowstacks.com/api/skills/funclip/claude-skill -o ~/.claude/skills/funclip/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How FunClip: Turn Videos into searchable subtitles and clips fast works

Codeflow

Free to inspect

FunClip: Turn Videos into searchable subtitles and clips fast is a small Python project (~2.4k lines across 17 code files, plus 21 test files). Setup is light: install Python, run one command. Last commit this month, MIT license, has a test suite.

Size

Small codebase

~2.4k lines · 17 code files · 20 min skim

Setup

Light setup

Install Python, run one command.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
requirements.txt
Dependencies and the commands it exposes
3
funclip/__init__.py
Inside funclip/ — the main logic begins here

What's in each folder

funclip/Core code — the actual logic19 files

docs/Documentation11 files

scripts/Helper scripts1 files

tests/Tests — proof it works19 files

.github/CI / automation (GitHub Actions)6 files

font/Images & static assets1 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/funclip && curl -fsSL https://workflowstacks.com/api/skills/funclip/claude-skill -o ~/.claude/skills/funclip/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

modelscope

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Turn meeting notes into a summary email automatically

Paste the transcript into a private form and the workflow writes and emails a concise recap — decisions, owners, open questions — that people will actually read.