Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
About this project
FunASR is an open-source speech and audio project on GitHub: Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving. It covers speech and audio, the layer that turns text into voice, voice into text, or raw audio into something structured. It is maintained by modelscope and published as a public repository you can read, fork and run yourself.
On GitHub the repository is tagged asr, audio, chinese, emotion-recognition, funasr, mcp-server, multilingual-asr, openai-compatible-api, paraformer and punctuation, which is a fair summary of what it covers. Most deployments care about latency and voice quality, so the project usually ships both a batch path and a streaming or real-time one.
It is written mainly in Python and released under MIT, a permissive license — commercial use is fine as long as copyright notices are kept. It is actively maintained: the most recent commit landed on November 17, 2026.
To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at www.funasr.com for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.
Key facts as recorded on GitHub: 21,063 stars; 2,134 forks; primary language Python; license MIT; last commit on November 17, 2026; topics asr, audio, chinese, emotion-recognition, funasr, mcp-server.