What it does
FunASR is a speech-recognition toolkit: it converts spoken audio into written text. It works on recordings and on live, streaming audio, and can run on servers or smaller devices.
Besides transcribing, it can find where speech starts and stops, add punctuation, tell different speakers apart, and detect emotions and sounds such as laughter or music. Different models cover Chinese, English, Japanese, Chinese dialects and, in one version, 31 languages.
It can be set up as a service that other apps call in the same way they would call OpenAI, and it connects to AI assistants through MCP.
Who it's for
Developers building transcription, captioning or voice features, especially with Chinese-language audio.
Can I use it without coding?
Developers only. A Python toolkit. Online notebook and demo versions let you try it in a browser. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe