FunASR
FunASR is an open-source speech recognition toolkit that turns recorded or live audio into text for developers and teams building transcription tools.
What it is good for
- Transcribing recorded meetings and audio files into text
- Adding live speech-to-text to a voice app
- Identifying who is speaking in a recording
- Running speech recognition offline on a local machine
At a glance
- Who it is for
- Setup
- Requires programming
Level 5 of 5. You need to write code to use it.
- Cost
- Free and open source
- Type
- Framework or SDK
- Tasks
- Works with
- Claude, Cursor, LangChain, Dify, AutoGen
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 20,913
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is FunASR free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use FunASR?
- Yes. You need to write code to use it.
- What does FunASR work with?
- According to its own documentation, it works with Claude, Cursor, LangChain, Dify, and AutoGen.
- What is FunASR good for?
- Transcribing recorded meetings and audio files into text, adding live speech-to-text to a voice app, identifying who is speaking in a recording, and running speech recognition offline on a local machine.
Similar agents to FunASR
- DeerFlow
DeerFlow is an open-source super agent that researches topics, writes code, and creates content over tasks that take minutes to hours, for people who need multi-step work done.
- DramaClaw
DramaClaw is a self-hosted video production line that turns a script into a finished film for creators who want to run it themselves.
- obsidian-second-brain
obsidian-second-brain is a skill plugin that gives Claude Code, Codex and other agents persistent memory stored in your Obsidian notes, for people who keep their knowledge in Obsidian.
- ffmpeg-skill
ffmpeg-skill is an Agent Skill that gives coding agents 42 local FFmpeg tools to cut, caption, reframe, and export video for creators.
- earshot
earshot is an agent app that lets coding agents hear and check sound for films, demos, and games for developers making sound in code.
- Ableton MCP
Ableton MCP is an MCP server that lets Claude control Ableton Live to create tracks, arrange clips, and compose music for music producers.