Skip to content
One model, built for telephony

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.

Call a live Omni agent+1 (252) 888-7924

Answered by a PyAI Omni agent · may be recorded.

Hear PyAI in 3 secondsLive

Tap a voice - no signup, no key.

Want it to say your own words?Open the Playground

0B+
Conversations powered across our portfolio - we know telephony
~0 ms
Omni voice-to-voice, in-region
$0.05/min
$3.00/hr all-in for Omni
No bill
Sandbox keys use daily caps, not credit
One engine, not four vendors

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.

Vapi / Retell / Bland: four bills, four markups
Speech-to-texte.g. Deepgram
Reasoning (LLM)e.g. OpenAI / Anthropic
Text-to-speeche.g. ElevenLabs
Orchestration + turn-takingthe advertised platform fee

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.

PyAI: one engine, one all-in minute
One speech-to-speech model
Speech + brain + retrieval + telephony, one loop
$0.05/min
all-in, per-second billed

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.

Human call center
$25-40/hr
The cost PyAI replaces.
Bland self-serve
$6.60-8.40/hr
Plus platform fees on paid plans.
Aircall AI Agent
$23-59/hr
Before base phone seats and add-ons.
Best value
PyAI Omni API
$3.00/hr
$0.05/min all-in.
Best value
PyAI Agents
$4.80/hr
$0.08/min, no code, no engineering.

Plugs into the stack you already run

Bring your number
TwilioJustCallTelnyxany SIP trunk
Push outcomes to
HubSpotSalesforceZapierwebhooks
How it works

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.

A call, end to end

Acme Dental’s front-desk agent - every step powered by PyAI.

TelephonyNumbers - SIP
HearSpeech-to-text
Turn detectionTurn-taking
Omni brainLLM + tools
SpeakText-to-speech
ActionsJSON - CRM

Hear <-> Speak repeats every turn, with barge-in - then the call becomes data.

Ready when you are.

Each step is a PyAI model. Press play to watch them hand off - or tap any stage to jump.

  • Hearpyai-hear
  • Omni brainpyai-omni-realtime
  • Speakpyai-voice
Turned into data

Transcript, summary, intent, and disposition - emitted as JSON when the call ends.

Pushed toHubSpotSalesforceZapier
Results

Teams book more - and resolve faster - with PyAI.

From AI appointment booking to compliance on every call, here's what customers see.

57%
incremental revenue from AI appointment booking
-80%
cost per resolution ($14 to $2.80)
<1 min
time to first reply
10k+
calls handled monthly across the SaaS Labs portfolio
Our AI Agents book appointments 24/7 - that drove 57% incremental revenue for our customers. It's our hottest-selling product.
SShaambhavProduct, ServiceAgent
We run healthcare and TCPA-heavy lines. Trace auto-scores every call against our rule packs, so compliance stopped being a fire drill.
DDanielDPO, JustCall
Time to first reply is under a minute and CSAT is at an all-time high - while our cost per resolution keeps dropping.
PNPriya NairDirector of CX, Helpwise
A real AMD decision, as your webhook receives it
{
  "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.

Pricing

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.

Omni API$0.05/min

Realtime voice agent API

Agents$0.08/min

Manage, evaluate & ship agents, no code

Trace$0.03/min

Compliance, QA, evals

Castfrom $0.02/min

Async emotional TTS

Hear starts at $0.001/min. Telephony, Recap, and KB Context are on the full rate card.

Free to start
Sandbox

Sandbox keys never bill. Live credit depends on verification and funding.

Build with the API
Build with AI

Using 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.

Open your tool
FAQ

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.