# Audial MCP

> Audial MCP is a freemium MCP server for design and media. MCP server for Audial's stem splitting, mastering, MIDI, lyrics and music generation. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, API, macOS, Windows, Linux
- **Website:** https://audialmusic.ai/resources/api-reference
- **Repository:** https://github.com/audialai/audial-mcp
- **MCP Registry name:** io.github.AudialAI/audial-mcp
- **Categories:** design and media
- **Listing updated:** 2026-11-14

## About

Audial's hosted audio tools become tool calls in Claude Code, Claude Desktop or Cursor. Beyond stems and mastering, it can find a song's sections and tempo map in about half a minute, add audio features, genre and mood tags and timed lyrics to that analysis, build sample packs, and turn a single isolated sound into an editable Vital or Serum 2 preset. It can also sing supplied lyrics in a reference voice.

There is no API key to copy: the first tool call opens a browser sign-in, saved to ~/.audial/credentials.json, and AUDIAL_API_KEY can be set for CI. Results are saved to a folder such as ~/Audial. Install with uvx audial-mcp or a Claude Desktop .mcpb bundle.

The pricing page lists a free demo tier with 10MB uploads, plus an enterprise plan by contact.

## Features

- **Stem separation:** Splits vocals, drums, bass and other.
- **Song analysis:** Sections, tempo, bars, features, tags and lyrics.
- **Mastering:** Masters tracks, optionally matched to a reference.
- **Synth presets:** Turns one sound into a Vital or Serum 2 preset.
- **Music generation:** Text to music, covers and remixes.

## Good for

- Split a track into stems for remixing
- Master a demo to match a reference
- Extract timed lyrics
- Make a sample pack from a song

## Install

### Claude Code (Terminal)

```sh
claude mcp add audial-mcp --env AUDIAL_API_KEY='<AUDIAL_API_KEY>' -- uvx audial-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ],
      "env": {
        "AUDIAL_API_KEY": "<AUDIAL_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ],
      "env": {
        "AUDIAL_API_KEY": "<AUDIAL_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "audial-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "audial-mcp"
      ],
      "env": {
        "AUDIAL_API_KEY": "<AUDIAL_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ],
      "env": {
        "AUDIAL_API_KEY": "<AUDIAL_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ],
      "env": {
        "AUDIAL_API_KEY": "<AUDIAL_API_KEY>"
      }
    }
  }
}
```

## Tools

- `stem_split`: Split a track into vocals, drums, bass and other.
- `analyze`: BPM, key and other characteristics.
- `segment`: Song sections, tempo and bars; returns an analysis_id.
- `audio_features`: Energy, danceability, loudness, mode, key and tatum.
- `tag_audio`: Genre, moods, instruments and artist tags.
- `get_lyrics`: Lyrics as timed lines.
- `master`: Mastering, optionally matched to a reference.
- `generate_samples`: Sample pack from an analysis or file.
- `generate_midi`: Audio to MIDI.
- `generate_music`: Text to music, covers and remixes.
- `sound2vital`: One isolated sound to an editable Vital preset.
- `sound2serum`: One isolated sound to a Serum 2 preset.
- `text2vox`: Lyrics and reference voice to a sung vocal and MIDI.
- `pipeline_status`: State of a pipeline and its outputs.
- `service_status`: Which tools have a worker awake and cold-start cost.
- `list_results`: Browse previous results.

## FAQ

### Do I need an API key?

No, a browser sign-in handles it, or set AUDIAL_API_KEY for servers.

### Is there a free tier?

A free demo tier is listed with a 10MB upload cap.

### How do I install it?

uvx audial-mcp, or the Claude Desktop bundle.

### Is Audial MCP free?

Audial MCP has a free plan, with paid plans for more usage or features.

### How do I add Audial MCP to Claude Code?

Run this command in your terminal: claude mcp add audial-mcp --env AUDIAL_API_KEY='<AUDIAL_API_KEY>' -- uvx audial-mcp

### What are the best alternatives to Audial MCP?

The closest alternatives to Audial MCP are HyperFrames by HeyGen, ffmpeg-skill, AvatarSay — Fictional Character & Talking Video MCP, ChartAnt and VfxSmith.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [Hourlore](https://ai-powered.com/mcp/hourlore): Hourlore is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/audial-mcp
