io.github.chicogong/ffvoice

not probeable (local package)

Unclaimed · Unverified

Publisher-provided description

Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud

Summary by lookupd

Transcribes audio files on-device and separates speakers, with no cloud calls, so an agent can get speaker-labeled text locally.

Install

Claude Code, pypi package (stdio)

claude mcp add ffvoice -- uvx ffvoice

Codex, pypi package (stdio)

codex mcp add ffvoice -- uvx ffvoice

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "ffvoice": {
      "command": "uvx",
      "args": [
        "ffvoice"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.chicogong/ffvoice.svg)](https://lookupd.com/servers/io.github.chicogong/ffvoice)