Skip to content

Feature Proposal: Add FunASR Speech-to-Text Tool #398

Description

@LauraGPT

The Cloudflare MCP server enables AI clients to interact with Cloudflare services. Adding a FunASR speech-to-text tool would enable voice-triggered workflows and audio content analysis via MCP.

FunASR (17.8K+ stars, https://github.com/modelscope/FunASR) provides:

  • SenseVoice: Ultra-fast multilingual ASR (50x faster than Whisper-large)
  • OpenAI-compatible API: POST /v1/audio/transcriptions

Use cases:

  1. Voice-triggered Cloudflare Workers — user speaks, FunASR transcribes, MCP tool processes
  2. Audio content analysis — transcribe audio stored in R2, then process via other MCP tools
  3. Accessibility — add transcription to audio assets in Cloudflare CDN

Would adding a FunASR transcription tool be useful?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions