FunClip
A video transcription and subtitle generation tool with LLM-assisted functionality.
GraphCanon updated 3w · GitHub synced 3w · 103 views this month
Decision brief
FunClip is a Python-based video transcription and subtitle generation tool with local Gradio UI interface that leverages ASR technology, offering alternatives to Whisper while supporting LLM-assisted functionalities.
Good fit when
- When you need to transcribe videos in Chinese, as FunClip may have optimized speech recognition for the language.
- For users familiar with Python who prefer open-source tools under MIT License.
Avoid when
- When the primary focus is on extensive video editing features beyond subtitle embedding, as FunClip primarily serves speech-to-text transcription needs.
- For projects that strictly avoid installing external tools, such as ffmpeg and imagemagick, necessary for full functionality.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- 87 low (87 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install FunClipSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
FunClip integrates speech recognition for creating transcriptions and subtitles automatically from videos, featuring a local Gradio UI interface. It offers an alternative to Whisper with functionalities like ASR and video editing capabilities that include embedding subtitles into video clips.
Capability facts
- Languages
- python
Source: github.language · Jul 30, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 30, 2026)
### Python env installSource link
Tags
README
Python env install
FunClip basic functions rely on a python environment only.
---
# install Python requirments
pip install -r ./requirements.txt
For a versioned snapshot, download FunClip-2.1.0.tar.gz or FunClip-2.1.0.zip, then verify it with the published SHA256SUMS. Model weights are downloaded separately when FunClip starts and are not included in these source archives.
FunClip's Fun-ASR-Nano, SenseVoice, and subtitle compatibility paths require funasr>=1.3.29. This release returns every SenseVoice VAD region through sentence_info when token timestamps are unavailable, so clipping and subtitle clients receive segment boundaries instead of an empty timeline. It also includes the real-time final-text and short-tail fixes from 1.3.28. If you installed FunClip before this requirement was updated, run pip install -U "funasr>=1.3.29" before starting the Gradio service. Release notes · PyPI
imagemagick install (Optional)
If you want to clip video file with embedded subtitles
- ffmpeg and imagemagick is required
- On Ubuntu
apt-get -y update && apt-get -y install ffmpeg imagemagick
sed -i 's/none/read,write/g' /etc/ImageMagick-6/policy.xml
- On MacOS
brew install imagemagick
sed -i '' 's/none/read,write/g' "$(brew --prefix imagemagick)/etc/ImageMagick-7/policy.xml"
- On Windows
Download and install imagemagick https://imagemagick.org/script/download.php#windows
Find your python install path and change the IMAGEMAGICK_BINARY to your imagemagick install path in file site-packages\moviepy\config_defaults.py
- Download font file to funclip/font
wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ClipVideo/STHeitiMedium.ttc -O font/STHeitiMedium.ttc
License
- FunClip source code is licensed under the MIT License.
- Model weights are downloaded separately and are governed by the terms on their model pages. The default Paraformer-Large, SeACo-Paraformer, and CAM++ pages currently list Apache License 2.0; check the applicable model page before redistribution.
For agents
This page has a .md twin and JSON over the API.