Audial Mcp

io.github.AudialAIv0.1.1Updated Sep 29, 2026

Audial audio tools: stems, analysis, mastering, sample packs, MIDI, music generation, vocals.

VerifiedSTDIODesktop onlyData & AnalyticsMedia & Design

Installation

In SourceWeft

  1. Open Audial Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

audial-mcp

Run Audial's hosted audio tools from any MCP client: split stems, analyze and segment audio, master tracks, build sample packs, convert audio to MIDI, generate music, turn a one-shot into an editable Audial Synth preset, and sing lyrics in a reference voice.

mcp-name: io.github.AudialAI/audial-mcp

Install

You need an Audial account (user id + API key from https://audialmusic.ai) and uv.

Claude Code

bash
claude mcp add audial \  -e AUDIAL_USER_ID=your-user-id -e AUDIAL_API_KEY=your-api-key -e AUDIAL_RESULTS_DIR=~/Audial \  -- uvx audial-mcp

Claude Desktop / Cursor / any client with a JSON config

json
{  "mcpServers": {    "audial": {      "command": "uvx",      "args": ["audial-mcp"],      "env": {        "AUDIAL_USER_ID": "your-user-id",        "AUDIAL_API_KEY": "your-api-key",        "AUDIAL_RESULTS_DIR": "~/Audial"      }    }  }}

Tools

ToolWhat it does
stem_splitSplit a track into vocals, drums, bass, other (optionally retime / rekey)
analyzeBPM, key and other characteristics
segmentSections and component analysis
masterMastering, optionally matched to a reference
generate_samplesSample pack from a track
generate_midiAudio to MIDI
generate_musicText to music, covers, remixes, extraction, completion with the Audial music model
sound2vitalOne-shot → editable Audial Synth (Vital) preset
text2voxLyrics + reference voice → sung vocal and MIDI
list_resultsBrowse previous results in your results folder

What leaves your machine

Audio and text you pass to a tool are uploaded to Audial's API (https://api.audialmusic.ai) over HTTPS and processed on Audial's servers; results are downloaded into AUDIAL_RESULTS_DIR (default ~/Audial). Nothing else is sent.

Two other files are read if they exist, because the Audial SDK looks for them: ~/.audial/.audial_config.json and a .env in the directory the server was started from. Credentials from your MCP client's config always win: audial-mcp snapshots its environment before the SDK loads either file, so neither can redirect your credentials or the API host.

Every tool except list_results calls the Audial API, which requires an active Audial subscription on the account; without one the tool returns the API's subscription message.

Configuration

VariableRequiredDefault
AUDIAL_USER_IDyes
AUDIAL_API_KEYyes
AUDIAL_RESULTS_DIRno~/Audial
AUDIAL_JOB_TIMEOUT_Sno900
AUDIAL_API_BASE_URLnoproduction API

License

MIT. Source: https://github.com/AudialAI/audial-mcp

Source: README.md at commit 00e6dee

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.1LatestSep 29, 2026