Integration

AudioCraft integration

Meta's AudioCraft AI music generation platform powered by MusicGen, accessible via Replicate. Generate high-quality music from text descriptions, continue audio tracks, apply melody conditioning, and create professional soundtracks. Features multiple model variants including stereo-melody-large (flagship), stereo-large, melody-large, and large for different use cases.

Connect AudioCraft How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AudioCraft.Built from the 9 AudioCraft tools below, on the connection you add once.

Common AudioCraft use cases

View generation history
Extend short music loops
Cancel unwanted generations
Create variations on melodies
Understand model capabilities
Poll for generation completion
Maximum quality mono generation
Discover available model variants
Create background music for videos
Build usage dashboards

What you can do with AudioCraft

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Audio, 4 operations

continue_audioContinue audioPOSTExtends existing audio by generating a seamless continuation from the input track.
generate_musicGenerate musicPOSTGenerates high-quality music from text descriptions using Meta's MusicGen AI model on Replicate.
generate_music_melodyGenerate music melodyPOSTGenerates music influenced by a reference melody audio while following text prompts using melody conditioning.
generate_music_with_diffusionGenerate music with diffusionPOSTGenerates music using MultiBand Diffusion decoding for enhanced audio quality on non-stereo models.

Prediction, 3 operations

cancel_predictionCancel predictionPOSTCancels a running music generation prediction before completion.
get_predictionGet predictionGETRetrieves the status and output of an asynchronous music generation prediction.
list_predictionsList predictionsGETLists recent music generation predictions with pagination support.

Model, 2 operations

get_model_infoGet model infoGETRetrieves detailed information about the MusicGen model including parameters and documentation.
list_model_versionsList model versionsGETRetrieves available MusicGen model versions with their capabilities and version IDs.

Use AudioCraft from Claude Code, Cursor or Codex

Connect AudioCraft in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AudioCraft operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect AudioCraft

Create your workspace
Sign up free. Nothing to install.
Connect AudioCraft once
Add your AudioCraft connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

AudioCraft integration FAQ

What can you do with the AudioCraft integration?

LiveContext exposes 9 operations on AudioCraft, covering audio, prediction and model. Common uses include View generation history, Extend short music loops and Cancel unwanted generations.