Funasr Transcribe
Funasr Transcribe processes audio and video files into structured Markdown transcripts with precise timestamps and speaker identification. It supports multiple formats (mp4, mov, mp3, wav, m4a, flac) and offers ONNX-accelerated recognition modes for faster processing. The skill automatically extracts video keyframes, generates AI-powered summaries, and handles both single-speaker and multi-speaker scenarios.
Funasr Transcribe converts audio and video files to timestamped text using local FunASR speech recognition.
AI-generated summary based on this skill's SKILL.md
Install
cat-xierluo/legal-skills/funasr-transcribe · repository language: Python
git clone https://github.com/cat-xierluo/legal-skills
cp -r legal-skills ~/.claude/skills/funasr-transcribegenerated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
npx skillfed install cat-xierluo/legal-skills/funasr-transcribeFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What audio formats does Funasr Transcribe support?
Funasr Transcribe processes multiple audio and video formats including mp4, mov, mp3, wav, m4a, and flac. The skill converts these files into structured Markdown transcripts with precise timestamps and speaker identification, making it easy to search and reference your audio content.
How do I transcribe audio to text with Funasr Transcribe?
Funasr Transcribe automatically converts your audio files into written text transcripts. Simply provide your audio or video file, and the skill performs automatic speech recognition, extracting the spoken content and organizing it with timestamps. For faster processing, you can use ONNX-accelerated recognition modes.
Can Funasr Transcribe handle multiple speakers?
Yes, Funasr Transcribe handles both single-speaker and multi-speaker scenarios. The skill identifies different speakers and includes speaker identification in your transcript, making it clear who said what throughout your audio content.
What additional features does Funasr Transcribe offer?
Beyond transcription, Funasr Transcribe automatically extracts video keyframes and generates AI-powered summaries of your content. These features help you quickly understand and navigate your audio and video files without listening to the entire recording.
Does Funasr Transcribe work with video files?
Funasr Transcribe processes both audio and video files. It transcribes the speech from video content and can extract keyframes, making it useful for converting video recordings, presentations, and multimedia content into searchable text transcripts with timestamps.