# AudioPod AI (core)

A hosted MCP server for transcribing, splitting, cleaning, and converting audio you already have. Use it when an agent needs audio processing without local models.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: AudiopodAI
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AudiopodAI/audiopod-mcp
- Updated: 2026-10-14
- HTML: https://affpapa.org/en/nevibecode/mcp/audiopod-ai-core

## What it does

AudioPod AI (core) connects an agent to the remote endpoint `https://mcp.audiopod.ai/core`. Its tools can transcribe recordings with speaker labels and SRT/VTT subtitles, split tracks into stems, remove background noise, put speakers on separate tracks, convert media, and turn audio into MIDI. The core endpoint exposes 9 tools, including job, account, and profile checks.

Long-running operations return a `job_id`; the agent can query it with `check_job_status`. On the first use, the client opens an OAuth 2.1 sign-in window. CI and headless runs use an API key sent through `X-API-Key`. The service is remote, so local models and a GPU are not needed.

Core works with audio you already have and does not create new audio. Music generation and speech synthesis belong to the full endpoint instead.

## Requirements
- Remote server: `https://mcp.audiopod.ai/core`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http audiopod-core https://mcp.audiopod.ai/core
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add audiopod-ai-core --url https://mcp.audiopod.ai/core
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "audiopod-ai-core": {
            "url": "https://mcp.audiopod.ai/core"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "audiopod-ai-core": {
            "type": "http",
            "url": "https://mcp.audiopod.ai/core"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http audiopod-ai-core https://mcp.audiopod.ai/core
```

## When to use it
- transcribe a recording with speaker labels
- produce SRT or VTT subtitles from audio
- split a track into vocal and instrumental stems
- remove background noise from a voice recording
- convert a recording into MIDI

## Example prompts
- Transcribe `meeting.wav`, label each speaker, and return an SRT file.
- Remove background noise from `interview.m4a` while keeping the voice character.
- Split `song.mp3` into stems and report the job status.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md