One voice model for phone agents. Not seven stitched boxes.
Stop gluing STT, an LLM, and TTS together like Vapi or Retell. Omni is one speech-to-speech model built for telephony, audio in, audio out, OpenAI-compatible, $0.05/min all-in. Start free, no card.
Answered by a PyAI Omni agent · may be recorded.
Tap a voice - no signup, no key.
Want it to say your own words?Open the Playground
One speech-to-speech model, built for the phone.
Vapi, Retell, and Bland stitch four vendors into every call, and the advertised platform fee is only one of the four bills. PyAI runs the whole call on one engine: ~390 ms median voice-to-voice in-region, first audio from Speak in ~53 ms warm in-region, and one all-in minute at $0.05.
The advertised platform fee is just the orchestration layer. Add the model, the voice, and telephony and the all-in minute lands at $0.10-0.31/min on the packaged platforms - plus the latency of every hop.
Public all-in ranges, Jun 2026 - advertised vs all-in, verify on each provider’s site.
One engine means no stacked vendor markups and no stacked latency - so the price is the price: one all-in minute, lower than any packaged platform. No platform fee to clear before the rate counts, no four-way bill to reconcile.
Four products to build on. One free way to start.
Omni API, Agents, Trace, and Cast carry production voice work. Hear, Speak, Telephony, AMD, and Recap are the building blocks underneath.
Omni
The definitive all-in-one AI voice agent model. Hybrid speech-to-speech, fused LLM brain, emotion-aware voices, and tool calling.
Agents
Launch and manage AI voice agents without code.
Cast
Cinematic, emotional long-form TTS for podcasts, narration, and audiobooks.
Trace
Bulletproof compliance & QA on every single call, automatically.
Start with an instant sandbox key
Sandbox keys work immediately with daily limits and never bill. Create an account to save projects, then fund a live key when you are ready for production traffic.
Plugs into the stack you already run
Watch a call flow through PyAI, end to end
Tap play. One front-desk call - ring to CRM - with every step powered by a PyAI model you can click into.
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 - Omni brain
pyai-omni-realtime - Speak
pyai-voice
Transcript, summary, intent, and disposition - emitted as JSON when the call ends.
Teams book more - and resolve faster - with PyAI.
From AI appointment booking to compliance on every call, here's what customers see.
“Our AI Agents book appointments 24/7 - that drove 57% incremental revenue for our customers. It's our hottest-selling product.”
“We run healthcare and TCPA-heavy lines. Trace auto-scores every call against our rule packs, so compliance stopped being a fire drill.”
“Time to first reply is under a minute and CSAT is at an all-time high - while our cost per resolution keeps dropping.”
{
"event": "amd",
"call_id": "CA7d0…",
"answered_by": "screening",
"answered_by_twilio": "machine_start",
"confidence": 0.96,
"decision_ms": 720,
"reason": "screening phrase: 'the person you're calling is using \
a screening service' at 0.6s"
}Every AMD decision carries a reason you can read. See how AMD works.
Test without billing. Fund production when ready.
Sandbox keys use daily caps and never bill. Agents is live in beta. Live keys consume prepaid credit.
Realtime voice agent API
Manage, evaluate & ship agents, no code
Compliance, QA, evals
Async emotional TTS
Hear starts at $0.001/min. Telephony, Recap, and KB Context are on the full rate card.
Sandbox keys never bill. Live credit depends on verification and funding.
Build with the APIUsing Cursor, Claude Code, Codex, or Lovable?
Start with one prompt. We hand your agent the API contract, the SDKs, and a free test key - so it writes correct PyAI code on the first try.
Questions, answered
Is PyAI OpenAI-compatible?
Yes. Point your OpenAI SDK at https://api.pyai.com/v1 with your PyAI key. Transcription and speech keep the same request and response shapes, and errors come back in the OpenAI envelope.
How much does it cost?
Hear is $0.001/min, Omni API is $0.05/min all-in, and Agents Beta is $0.08/min. Sandbox keys never bill. Live usage requires available credit.
Is it good for telephony?
That's the focus. Hear is tuned for 8 kHz call audio with a ~185 ms first partial (in-region), and Omni runs phone agents at human conversational pace, ~390 ms median voice-to-voice in-region, with barge-in.
Do I need a credit card to start?
No. An instant sandbox test key works without a card and never touches billing. Create an account to save projects. Add funding when you move a live key to production traffic.
Choose how you want to start.
Start with an instant sandbox key or launch Agents Beta without code. Sandbox usage never bills. Fund a live key when you are ready for production traffic.
Agents is live in beta. Sandbox keys have daily limits and never touch billing.