Omni
End-to-end realtime voice agents.
A single WebSocket that listens, thinks, and speaks - grounded in your knowledge bases and tools, with natural turn-taking and barge-in. All-in at $0.05/min, everything included.
- Price
- $0.05/min
- Endpoint
wss://api.pyai.com/v1/omni- Scope
omni:session- Model id
pyai-omni-realtime
Watch Omni run a call, end to end
Acme Dental’s front-desk agent - every step powered by PyAI.
Hear <-> Speak repeats every turn, with barge-in - then the call becomes data.
Each step is a PyAI model. Press play to watch them hand off - or tap any stage to jump.
- Hear
pyai-hear-telephony - Listening layer
internal - Omni brain
pyai-omni-realtime - Speak
pyai-voice
Transcript, summary, intent, and disposition - emitted as JSON when the call ends.
What you get
One socket, whole agent
Audio in, audio out. PyAI handles transcription, the reasoning brain, retrieval, and synthesis end to end.
Grounded and tool-using
Bind knowledge bases and webhook tools so the agent answers from your content and takes real actions.
Phone-ready turn-taking
Median turn-taking around 431 ms with barge-in, so conversations feel human, not walkie-talkie.
Median turn-taking ~431 ms; per-second billing with everything included at one flat rate.
Start in minutes
# Server-side clients may append the key to the URL.
url = "wss://api.pyai.com/v1/omni?agent_id=front_desk&api_key=pyai_live_..."
# Then stream pcm16 @ 24kHz up, receive agent audio down.FAQ
What is agent_id?
An opaque label authorized by your org - PyAI stores no per-agent state, so any id in your namespace works and is echoed to your own knowledge endpoint.
Is there an OpenAI-realtime-compatible URL?
Yes: wss://api.pyai.com/v1/realtime?model=pyai-omni-realtime&agent_id=<id>.
Build with Omni today.
Start free with $50.00 in credit - no card. Your test key works instantly.
No credit card - OpenAI-compatible - cancel anytime