Integration

Uberduck integration

Uberduck is a text-to-speech API that fronts several speech providers (Amazon Polly, Google Cloud TTS, Microsoft Azure) behind one call. List the available speech models and filter the voice library by language, gender, accent, age, mood, style or tag, then turn up to 10,000 characters of text into an MP3, WAV or OGG file returned as a download URL valid for 24 hours. Instant voice cloning (its audio-path input is not documented) and the conversational-agent call token (a LiveKit room session, not a REST result) are not exposed. Authentication is an API key from the Uberduck dashboard sent as a Bearer token in the Authorization header.

Connect Uberduck How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Uberduck.Built from the 3 Uberduck tools below, on the connection you add once.

What you can do with Uberduck

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.

Model, 1 operation

list_modelsList modelsGETList the text-to-speech models (Polly standard and neural, Google standard, WaveNet and Neural2, Azure neural) with their provider and features. Pass a model id as model to create_speech.

Speech, 1 operation

create_speechCreate speechPOSTTurn text (up to 10,000 characters) into speech with a voice from list_voices. Returns audio_url, a download link valid for 24 hours: download it to keep the file. Each call counts against the account's Uberduck plan quota.

Voice, 1 operation

list_voicesList voicesGETSearch the Uberduck voice library. Pass a returned voicemodel_uuid (polly_joanna, google_wavenet_a) as voice to create_speech. Filter by language, gender, accent, model or tag; page with limit and offset.

Use Uberduck from Claude Code, Cursor or Codex

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

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