Skip to content
AudioPod MCP

AudioPod MCP

by AudioPod AI
Released
Repository Docs
Files & Storage

Summary

Hosted audio-AI tools for agents: speaker-labelled transcription, stem splitting, noise removal, MIDI conversion, speech and music. No install or GPU needed.

Features

  • Full endpoint: 18 tools for transcription, stems, noise removal, speakers, MIDI, conversion, speech, voices and music
  • Core endpoint: 9 analysis-only tools that never generate new audio
  • Speaker-labelled transcription and speaker separation
  • OAuth 2.1 sign-in or X-API-Key for headless use
  • Streamable HTTP transport with published discovery card
  • No local install, models or GPU

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "AudioPod MCP" tools will be available.
{
  "mcpServers": {
    "audiopod-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.audiopod.ai"
      ]
    }
  }
}

Description

AudioPod's MCP server is a hosted endpoint that gives an AI agent a full audio workstation: nothing to install, no local models and no GPU. Connect it from Claude Desktop, Claude Code, Cursor, Continue, Cline, Goose or Codex and the agent can work on audio files directly.

There are two endpoints. The full server exposes 18 tools covering transcription with speaker labels, stem separation, noise removal, speaker separation, MIDI extraction, audio conversion, speech generation, voices and music. The core endpoint exposes 9 tools that only process audio you already have and never create new audio, which suits teams that want analysis and clean-up without generative output.

Authentication is OAuth 2.1, where the client opens a sign-in window on first use, or an X-API-Key header for CI and headless runs (free keys are available from the AudioPod dashboard). The transport is Streamable HTTP, and the server publishes a discovery card plus an unattended-install guide aimed at agents. A companion plugin bundle wraps the server with task skills for the major agent CLIs.

Useful for podcasters, editors and researchers who want an assistant to transcribe an interview, isolate vocals, clean a noisy recording or turn a melody into MIDI as part of a larger workflow.

Related MCP Servers

MCP: ElevenLabs

by ElevenLabs

Featured

ElevenLabs' official MCP server — generate speech, clone voices, transcribe audio, and build voice agents.

Developer Tools

MCP: Fireflies.ai

by Fireflies.ai

Featured

Fireflies.ai's official remote MCP server — 19 tools for searching meeting transcripts and summaries, pulling action items and analytics, and cutting soundbites from recorded calls.

Productivity

MCP: Vapi MCP Server

by Vapi

Vapi's official MCP server for building voice agents — create assistants, place and schedule outbound phone calls, and manage phone numbers from your AI client.

Developer Tools
Browse all MCP servers →