Koskamo

ffvoice MCP

An offline speech-to-text and speaker diarization MCP server that allows AI agents to transcribe audio on-device using Whisper ASR without cloud dependency. It provides a pre-wired pipeline including microphone capture, denoising, VAD segmentation, and live captioning via a CLI and Python bindings.

Package and access

Local package with source-attributed installation metadata. Koskamo does not execute packages during review.

ffvoice MCP logo, by chicogongCommunity listingLocal stdioSource reviewed; not executedPublished by chicogong
Vendor documentation

What you can do with it

  • Transcribe audio on-device for AI agents
  • Perform speaker diarization locally
  • Generate live captions from microphone input
  • Run offline speech recognition without cloud APIs

Source and maintenance

Community listingRegistry 0.8.3
mcp-registry: io.github.chicogong/ffvoice@0.8.3Source repository
Maintenance checked

Packages and installation

Source-provided package data. Koskamo has not executed or live-probed this package.

ffvoice 0.8.3

pypiuvx
ffvoice package definition
{
  "version": "0.8.3",
  "transport": "stdio",
  "identifier": "ffvoice",
  "runtimeHint": "uvx",
  "registryType": "pypi",
  "registryBaseUrl": "https://pypi.org",
  "packageArguments": [
    {
      "name": "--from",
      "type": "named",
      "value": "ffvoice[mcp]",
      "description": "Install ffvoice with the MCP extra so the ffvoice-mcp entry point is available"
    }
  ]
}

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

Connect from your client

Each snippet configures the same source-provided package; replace placeholders before use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Cursor

Merge this local stdio configuration, replace every placeholder environment value, and restart Cursor. Koskamo has not executed this package.
Cursor configuration
{
  "mcpServers": {
    "ffvoice-mcp": {
      "command": "uvx",
      "args": [
        "ffvoice==0.8.3",
        "--from=ffvoice[mcp]"
      ]
    }
  }
}

Cline

Merge this local stdio configuration, replace every placeholder environment value, and restart Cline. Koskamo has not executed this package.
Cline configuration
{
  "mcpServers": {
    "ffvoice-mcp": {
      "command": "uvx",
      "args": [
        "ffvoice==0.8.3",
        "--from=ffvoice[mcp]"
      ]
    }
  }
}

VS Code

Merge this local stdio configuration, replace every placeholder environment value, and restart VS Code. Koskamo has not executed this package.
VS Code configuration
{
  "servers": {
    "ffvoice-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ffvoice==0.8.3",
        "--from=ffvoice[mcp]"
      ]
    }
  }
}

Claude Desktop

Merge this local stdio configuration, replace every placeholder environment value, and restart Claude Desktop. Koskamo has not executed this package.
Claude Desktop configuration
{
  "mcpServers": {
    "ffvoice-mcp": {
      "command": "uvx",
      "args": [
        "ffvoice==0.8.3",
        "--from=ffvoice[mcp]"
      ]
    }
  }
}

Let your agent find its tools

Find servers like ffvoice MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 4,304