{"data":{"slug":"modelscope-funclip","name":"FunClip","tagline":"A video transcription and subtitle generation tool with LLM-assisted functionality.","github_url":"https://github.com/modelscope/FunClip","owner":"modelscope","repo":"FunClip","owner_avatar_url":"https://avatars.githubusercontent.com/u/109945100?v=4","primary_language":"Python","stars":6332,"forks":753,"topics":["ai-tools","ai-video-editing","asr","auto-subtitles","chinese","content-creation","funasr","funclip","gradio","llm","paraformer","speech-recognition","speech-to-text","subtitles-generator","transcription","video-editing","video-processing","video-subtitles","video-transcription","whisper-alternative"],"archived":false,"github_pushed_at":"2026-09-16T02:01:36+00:00","maintenance_label":"Very active","stars_delta_30d":247,"url":"https://www.graphcanon.com/tools/modelscope-funclip","markdown_url":"https://www.graphcanon.com/tools/modelscope-funclip.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelscope-funclip","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelscope-funclip","description":"FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.","homepage_url":"https://huggingface.co/spaces/FunAudioLLM/FunClip","license":"MIT","open_issues":12,"watchers":45,"ai_summary":"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.","readme_excerpt":"### Python env install\n\nUse a separate Python environment for FunClip. The commands below use Python 3.12; install a matching PyTorch/torchaudio pair for your platform before the remaining requirements. See the [installation and troubleshooting guide](docs/installation.md#english) for the Linux CPU recipe, Windows activation and certificate errors.\n```shell\ngit clone https://github.com/modelscope/FunClip.git\ncd FunClip\npython3.12 -m venv .venv\n. .venv/bin/activate\npython -m pip install -r requirements.txt\npython -m pip check\npython funclip/launch.py --help\n```\n\nKeep this environment on the repository's **Transformers 4.x** requirements. Nano's separate native **Transformers 5.x** quickstart is not an upgrade command for an existing FunClip installation.\n\nFor a versioned snapshot, download [FunClip-2.2.1.tar.gz](https://github.com/modelscope/FunClip/releases/download/v2.2.1/FunClip-2.2.1.tar.gz) or [FunClip-2.2.1.zip](https://github.com/modelscope/FunClip/releases/download/v2.2.1/FunClip-2.2.1.zip), then verify it with the published [SHA256SUMS](https://github.com/modelscope/FunClip/releases/download/v2.2.1/SHA256SUMS). Model weights are downloaded separately when FunClip starts and are not included in these source archives.\n\nFunClip v2.2.1 keeps the supported Gradio 4 runtime and renders built-in subtitles with Pillow so the selected foreground color survives video encoding. Existing installations should run `python -m pip install -U -r requirements.txt` inside their FunClip environment before restarting.\n\nFunClip's current model and subtitle compatibility paths require `funasr>=1.4.9`. This includes the MOSS vLLM adapter, long-audio generation controls, normalized `sentence_info` speaker segments, and the earlier SenseVoice and realtime fixes. If you installed FunClip before this requirement was updated, run `python -m pip install -U \"funasr>=1.4.9\"` before starting the Gradio service. [Release notes](https://github.com/modelscope/FunASR/releases/tag/v1.4.9) · [PyPI](https://pypi.org/project/funasr/1.4.9/)\n\n---\n\n### imagemagick install (Optional)\n\nThe built-in subtitle renderer in v2.2.1 uses Pillow and the bundled font, so standard subtitle clipping no longer requires ImageMagick. Install ImageMagick only for the legacy `funclip/test/imagemagick_test.py` example or your own MoviePy `TextClip` workflow.\n<a name=\"Usage\"></a>\n\n---\n\n## License\n\n- FunClip source code is licensed under the [MIT License](./LICENSE).\n- Model weights are downloaded separately and are governed by the terms on their model pages. The default [Paraformer-Large](https://modelscope.cn/models/iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), [SeACo-Paraformer](https://modelscope.cn/models/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary), and [CAM++](https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) pages currently list Apache License 2.0; check the applicable model page before redistribution.","github_created_at":"2023-05-17T07:23:44+00:00","created_at":"2026-07-11T12:15:13.024994+00:00","updated_at":"2026-09-20T07:16:53.798796+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"ai-video-editing","name":"ai-video-editing"},{"slug":"asr","name":"asr"},{"slug":"auto-subtitles","name":"auto-subtitles"},{"slug":"funclip","name":"funclip"},{"slug":"gradio","name":"gradio"},{"slug":"llm-assisted","name":"llm-assisted"},{"slug":"speech-recognition","name":"speech recognition"},{"slug":"video-transcription","name":"video-transcription"}],"trust":{"provenance":{"is_fork":false,"github_id":641795100,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:16:51.444Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":4,"days_since_push":4,"last_release_at":"2026-09-01T06:37:27Z","stars_delta_30d":247,"open_issues_delta_30d":12},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":87,"high_count":0,"last_scan_at":"2026-07-11T12:15:14.804Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:16:52.460Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T07:16:52.460Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T07:16:52.460Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["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.","If you require embedding subtitles directly into video clips and possess additional software like imagemagick."],"when_not_to_use":["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.","If you need real-time processing or a cloud-based service rather than a tool that runs locally via its Gradio interface."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:12:02.908Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"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."}]}}