Skip to main content
Start with the job you have today. You can add the other paths later. Every path uses the same key and the same models.

Build with the API

Hear, Speak, Cast, or a raw Omni socket. Mint a sandbox key and make a first call.

Launch an Agent

Console workflow. Describe the job, test a call, put a Call Now button on your site or add a number.

Keep your framework

LiveKit or Pipecat owns the loop. PyAI is the speech layer: pyai.STT and pyai.TTS.

API primitives

Use this when you already own transport, the LLM, or turn policy.
  1. Mint a sandbox key (POST /v1/sandbox/keys).
  2. Transcribe with Hear or synthesize with Speak.
  3. Open Omni yourself with the browser voice agent guide when you want the full loop in code.
Authentication covers bearer keys, scopes, and the sandbox mint. Pricing is the rate card.

Console Agent

Use this when you want a voice agent on a website or phone number without standing up a token broker.
  1. Launch an Agent in the console.
  2. Add a hosted knowledge base so answers come from your pages and files. Paste a site URL and PyAI crawls the public pages.
  3. Publish the website Call Now button, or assign a number.
Creating the same profile from code is Create agents via API.

Framework adapters

Use this when LiveKit Agents or Pipecat should keep the session, tools, and LLM. These adapters use Hear and Speak. They do not create or select an Omni agent.

Next

Get a key

Console signup. Sandbox keys never bill.

Omni overview

One WebSocket for speech, reasoning, tools, and knowledge.