Integration

Bark integration

Bark is a transformer-based text-to-audio model by Suno AI that generates highly realistic, multilingual speech, music, and sound effects. Unlike conventional TTS systems, Bark directly transforms text into audio without intermediate phonemes, enabling natural speech patterns, emotional expressions, and non-verbal sounds like laughter and sighs. Hosted on Replicate for easy API access.

Connect Bark How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Bark.Built from the 12 Bark tools below, on the connection you add once.

Common Bark use cases

Create short jingles
Create audiobook narration
Cancel unwanted generations
Poll async generation status
Browse past audio generations
Create reusable voice profiles
Build serverless audio pipelines
Create character voices for games
Build real-time voice applications
Maintain consistent character voices

What you can do with Bark

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, 9 operations

generate_multilingual_speechGenerate multilingual speechPOSTGenerates natural speech in multiple languages using Bark's multilingual voice presets.
generate_musicGenerate musicPOSTGenerates short musical audio segments using musical notation markers in text prompts.
generate_sound_effectsGenerate sound effectsPOSTGenerates ambient sounds and audio effects using descriptive text prompts with sound markers.
generate_speechGenerate speechPOSTGenerates highly realistic speech audio from text using Bark's transformer-based text-to-audio model.
generate_speech_syncGenerate speech syncPOSTGenerates speech synchronously, waiting for completion before returning the response.
generate_speech_with_emotionGenerate speech with emotionPOSTGenerates speech with emotional expressions and non-verbal sounds using special markup in the text prompt.
generate_with_custom_voiceGenerate with custom voicePOSTGenerates speech using a custom voice profile from a previously generated .npz file.
generate_with_full_outputGenerate with full outputPOSTGenerates speech audio plus exports a reusable .npz voice profile file for consistent future generations.
generate_with_webhookGenerate with webhookPOSTGenerates speech asynchronously with webhook notification when generation completes.

Prediction, 3 operations

cancel_predictionCancel predictionPOSTCancels a currently running Bark audio generation prediction.
get_predictionGet predictionGETRetrieves the current status and output of a Bark audio generation prediction.
list_predictionsList predictionsGETRetrieves a paginated list of all predictions made by the authenticated user.

Use Bark from Claude Code, Cursor or Codex

Connect Bark in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Bark 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 Bark

Create your workspace
Sign up free. Nothing to install.
Connect Bark once
Add your Bark 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.

Bark integration FAQ

What can you do with the Bark integration?

LiveContext exposes 12 operations on Bark, covering audio and prediction. Common uses include Create short jingles, Create audiobook narration and Cancel unwanted generations.