funasr-mcp

IntegrationMedia

Turn audio files stored on your computer into written text without sending them anywhere. Once added, your AI can transcribe recordings using speech recognition that runs entirely on your own device, so your audio stays private.

This server has no hosted endpoint yet, so ahel can't serve it. You can still add it. It stays paused until ahel can serve it.

After adding it, point your AI at an audio file on your computer and ask it to turn the speech into text.

What your AI can do with it

  • Transcribe local audio files to text
  • Run speech recognition entirely on your own device
  • Keep recordings private since audio never leaves your computer
  • Transcribe speech using FunASR and SenseVoice models

Signals

GitHub stars
20k
Forks
2k
Last commit
Aug 2026
Advanced
Delivery
funasr-mcp MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
Catalog kind
mcp-server
Gateway key
io-github-modelscope-funasr-mcp
Source
github.com/modelscope/funasr