Integration

ReadAloud integration

ReadAloud is a low-cost text-to-speech API with an OpenAI-compatible speech route. Convert up to 5,000 characters of text into an audio file (mp3, opus, wav or raw pcm) in the default English voice, ten beta voices in German, Spanish, French, Italian and Brazilian Portuguese, or a voice already cloned for the account through ReadAloud's voice-cloning API (custom:<id>). Speech is billed per character from the account's credits: a one-time free allowance, then pay as you go once a payment method is added. Not offered: the WebSocket streaming and speech-to-text routes (they need a 60-second token), dubbing, voice conversion, voice design and audiobooks (signed-in session only), voice cloning (consent attestation and a zip upload) and the voice list (its answer is undocumented). Authentication is a ReadAloud API key (rtts_...) sent as a Bearer token; create it on readaloudai.org/developers.

Connect ReadAloud How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in ReadAloud.Built from the 1 ReadAloud tool below, on the connection you add once.

Common ReadAloud use cases

reading an article or summary aloud
voice prompts for phone agents

What you can do with ReadAloud

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

create_speechCreate speechPOSTAgents: ask firstConverts text (up to 5,000 characters) to speech and returns the audio file: mp3 by default, or opus, wav or raw pcm. Billed per character from the account's credits; answers 402 once the free allowance is used up without a payment method.

Use ReadAloud from Claude Code, Cursor or Codex

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

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

ReadAloud integration FAQ

What can you do with the ReadAloud integration?

LiveContext exposes 1 operation on ReadAloud, covering speech audio. Common uses include reading an article or summary aloud and voice prompts for phone agents.