FunASR

by modelscope · MCP 服务器 · ★ 20.2k

About FunASR

(简体中文한국어) Industrial speech recognition. 170x faster than Whisper. 50+ languages. Speaker diarization · Emotion detection · Streaming · One API call Quick Start · Benchmark · Use cases · Models · <

asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuation

Quick Facts

Stars20,231
Forks2,021
LanguagePython
CategoryMCP 服务器
LicenseMIT
Quality Score68.234495387616/100
Open Issues25
Last Updated2026-09-08
Created2022-11-24
Platformsmcp, python
Est. Tokens~16k

Compatible Skills

These tools work well together with FunASR for enhanced workflows:

  • textgen — semantic(0.17)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (59%)
  • ChatTTS — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • bailing — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (56%)

More MCP 服务器 Tools

Explore other popular mcp 服务器 tools:

View all MCP 服务器 tools →

Popular Python Agent Tools

Frequently Asked Questions

What is FunASR?

FunASR is Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.. It is categorized as a MCP 服务器 with 20.2k GitHub stars.

What programming language is FunASR written in?

FunASR is primarily written in Python. It covers topics such as asr, audio, chinese.

How do I install or use FunASR?

You can find installation instructions and usage details in the FunASR GitHub repository at github.com/modelscope/FunASR. The project has 20.2k stars and 2021 forks, indicating an active community.

What license does FunASR use?

FunASR is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse MCP 服务器 tools