skills.rest
cat-xierluo
cat-xierluoCOMMUNITY
Explore all skills by this author →
GitHub

funasr-transcribe

Transcribe audio and video files into timestamped Markdown documents using FunASR.

557|80|Updated Jan 7, 2026
Search Tags:#markdown#speech recognition#transcription#funasr#ai summary#audio to text#video to text
One-click install
npx skills add https://github.com/cat-xierluo/legal-skills --skill funasr-transcribe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: funasr-transcribe
Source: https://github.com/cat-xierluo/legal-skills/tree/main/skills/funasr-transcribe
Command: npx skills add https://github.com/cat-xierluo/legal-skills --skill funasr-transcribe

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fastapi, uvicorn, funasr, modelscope, torch, torchaudio, openai, httpx, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of converting audio and video files into accurate, timestamped Markdown transcriptions, saving significant time and effort compared to manual transcription.

Core Features & Use Cases

  • Versatile Format Support: Transcribes a wide range of audio and video formats (mp4, mov, mp3, wav, m4a, etc.).
  • Timestamped Output: Generates Markdown with precise timestamps for each transcribed segment.
  • Speaker Diarization: Optionally identifies and separates different speakers in the audio.
  • AI Summarization: Integrates with Claude Code to generate structured summaries (full summary, speaker summaries, key points, keywords) directly within the Markdown.
  • Use Case: Transcribe a recorded meeting to quickly generate minutes, identify action items, and summarize key discussion points. Or, convert a YouTube tutorial video into a searchable, timestamped transcript with a concise summary for easy review.

Quick Start

Use the funasr-transcribe skill to convert the audio file 'meeting_recording.mp3' into a timestamped markdown file.

Frequently Asked Questions about funasr-transcribe

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert audio to text with timestamps for meeting recordings?▼

Yes, you can transcribe video files to text. This Skill supports versatile video formats like mp4 and mov, automatically extracting audio to generate timestamped Markdown transcriptions using the FunASR engine.

Do I need to set up a local FunASR service to perform speaker diarization?▼

Yes, local FunASR service setup and model downloads are required to perform speaker diarization. The Skill automates identifying and separating different speakers in the audio using this local environment.

Can I generate an AI summary directly within my audio transcription output?▼

Yes, you can generate an AI summary directly within your transcription. It integrates with Claude Code to produce structured Markdown outputs containing full summaries, speaker summaries, key points, and keywords.

What's the best way to transcribe a YouTube tutorial video into searchable Markdown?▼

To transcribe a video into searchable Markdown, this Skill processes the video file through the FunASR engine, generating a timestamped transcript and optional concise summary for easy review.

Does audio to text transcription with FunASR require installing PyTorch and ModelScope?▼

Yes, audio to text transcription with FunASR requires installing PyTorch and Modelscope. These dependencies are necessary to run the local service and download the required models for operation.

Related Skills

Explore More Content & Communication Skills→
yangwhaleyangwhale
9

vllm-installer

Install, configure, and run vLLM on NVIDIA GPUs with CUDA.

Community
Advanced
sltc-devsltc-dev

meeting-summary

Refine raw meeting transcripts into structured summaries with action items and decisions.

Community
Intermediate
ericgandradeericgandrade
65

audio-transcriber

Transcribe audio recordings into structured Markdown documents with summaries.

Community
Advanced
adiytharpansaadiytharpansa

openai-whisper

Transcribes audio files to text or translated subtitles using the Whisper CLI locally without remote APIs.

Community
Basic