freeaudiototext-mcp

Transcrição de áudio e vídeo por IA 100% gratuita com diarização de falantes e suporte ao YouTube.

Documentação

FreeAudioToText MCP Server

An official Model Context Protocol (MCP) server for FreeAudioToText.com, enabling Claude, Cursor, and Codex to instantly transcribe any audio/video file or YouTube/TikTok URL into text with speaker diarization.

Our core transcription service is 100% free with unlimited usage. It runs on high-performance local Apple Silicon M2 Max hardware via the Cloudflare Edge, providing ultra-fast inference with state-of-the-art accuracy across 90+ languages.

Important Links

Website: https://freeaudiototext.com
Speech-to-Text API Documentation: https://freeaudiototext.com/speech-to-text-api
Get API Key / Dashboard: No API key is required for basic MCP tool usage! Our core transcription is fully free.

Available Tools

This MCP server exposes the following tools to your AI assistant:

transcribe_audio: Uploads a local audio or video file (e.g., MP3, M4A, WAV, MP4) for transcription. Returns a unique job_id.
transcribe_from_url: Submits a YouTube or TikTok URL for extraction and transcription. Returns a job_id.
get_job_status: Checks if the submitted job_id is "pending" or "completed".
get_transcript: Retrieves the full generated transcript (with speaker labels like [SPK_0]) for a completed job.
generate_ai_report: Generates a deep LLM analysis report (Summary, Action Items, Outline, or Speaker Analysis) for your transcript.

Installation

For Claude Desktop

Add the following to your claude_desktop_config.json (located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "freeaudiototext": {
      "command": "npx",
      "args": [
        "-y",
        "freeaudiototext-mcp"
      ]
    }
  }
}

For Cursor / Other Clients (via Smithery)

You can easily install this server using the Smithery CLI:

npx -y @smithery/cli install freeaudiototext-mcp --client cursor

Example Usage with Claude

Once installed, you can simply ask Claude:

"I have a meeting recording at /Users/myname/Downloads/meeting.m4a. Can you transcribe it and give me the action items?"

Claude will automatically:

Call transcribe_audio with your local file path.
Poll get_job_status until it finishes.
Call generate_ai_report with type action_items to give you the results!

License

MIT License. See LICENSE for more information.