Skip to content
Voice AI for telephony

Voice AI for phone agents. $0.05/min. OpenAI-compatible.

Build a realtime phone agent and log every call for compliance - all on one OpenAI-compatible API. Start free with $50 in credits. No card.

$50 in free credits - no card

Hear PyAI in 3 secondsLive

Tap a voice - no signup, no key.

Hear it say your words178 left

Want the full thing - Hear, Omni, code export?Open the Playground

$0.05/min
$3.00/hr for Omni API
~0 ms
Median Omni turn-taking
$0.08/min
Managed Omni Agents
0
Free transcription minutes / month

See where your voice AI budget leaks

Compare labor, platform fees, and all-in agent minutes before you commit to another stitched stack.

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.
PyAI Omni API
$3.00/hr
$0.05/min all-in.
PyAI Managed Agent
$4.80/hr
$0.08/min for managed runtime.
Receipts, not claims

Live latency receipts, refreshing every couple of seconds. Publish measured p50/p95/p99, then verify against your own call scripts.

Speak - time to first byte
32-98 ms
P95 <120 ms - P99 <180 ms
Omni - turn-taking
~431 ms p50
P95 ~690 ms - P99 ~890 ms
Hear - first partials
~300 ms p50
P95 ~520 ms - P99 ~700 ms
PyAI Omni
One engine
~431 ms p50
STT + reasoning + retrieval + TTS in one loop
Multi-vendor stack
Carrier -> orchestrator -> STT -> LLM -> TTS
2-4x typical
More network hops, more provider queues
Enterprise platforms
Hosted agent platform
~800 ms public-review anchor
Verify with your own call scripts

Powering voice & messaging for teams like

JustCallServiceAgentHelpwise

Plugs into the stack you already run

Bring your number
TwilioJustCallTelnyxany SIP trunk
Push outcomes to
HubSpotSalesforceZapierwebhooks
Built for both sides of the house

Developers ship in two lines. Teams launch with no code.

Whether you write the integration or describe the agent, PyAI meets you where you are.

For developers

Keep your OpenAI SDK. Change two lines, pass a PyAI key, and you have transcription, speech, and realtime agents - typed SDKs, idempotency, and stable error codes included.

Speak - text to speech
curl https://api.pyai.com/v1/audio/speech \
  -H "Authorization: Bearer $PYAI_KEY" \
  -d '{"model":"pyai-voice","input":"Hello from PyAI."}' \
  --output hello.mp3

For teams

Describe a phone agent in plain English, ground it in your docs, give it tools - and point your number at it. A working receptionist that books, answers, and transfers, in minutes.

  • No-code agent builder in the console
  • Answers from your knowledge base
  • Books, sends, and warm-transfers via tools
  • Pennies per minute, everything included
The models

Four products that matter. One free way in.

Omni API, Omni Agents, Trace, and Cast are the money products. Hear is the free developer wedge. Speak, Telephony, and Recap are primitives or add-ons underneath the stack.

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
Listening layerTurn-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-telephony
  • Listening layerinternal
  • Omni brainpyai-omni-realtime
  • Speakpyai-voice
Turned into data

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

Pushed toHubSpotSalesforceZapier
Why PyAI

Best price. Best latency. Built for the phone.

The boring stuff done right, so your agents are fast, cheap, and trustworthy.

The best price per minute

Omni API is $0.05/min all-in and transcription is $0.003/min - with per-second AI billing and telephony split out separately.

Telephony-native

Hear is tuned for 8 kHz call audio and Omni is built for phone turn-taking and barge-in - not repurposed studio models.

OpenAI-compatible

Keep your SDK and your error handling. Change base_url and key; everything else just works.

Realtime and fast

Speak streams from the first byte (~32-98 ms) and Omni answers with ~431 ms median turn-taking.

Grounded and tool-using

Bind knowledge bases and webhook tools so agents answer from your content and take real actions.

Honest billing

Per-second metering rounded once at the invoice, a clear rate card, and free credit to start. No surprises.

SOC 2 compliant

Independently audited security controls protect your data - and your callers'.

HIPAA-ready

A Business Associate Agreement and custom data terms for regulated teams.

Tamper-evident audit trail

Trace stamps every call with a verifiable audit hash and findings that cite the rule.

99.99% uptime

Real-time status and incident history at status.pyai.com.

OpenAI-compatible

Point your existing SDK at our base URL - keep your code and error handling.

A human answers

Reply to any email and a person reads it - not a ticket queue.

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 every month
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
Pricing

One hero number, then clear packages.

Start free with $50 in credits and 10,000 free speech-to-text minutes every month. Pay for Omni, Agents, Trace, and Cast when they create value.

Omni API$0.05/min

Realtime voice agent API

Omni Agents$0.08/min

Managed agents with evals and Recap included

Trace$0.05/min

Compliance, QA, evals

Castfrom $0.02/min

Async emotional TTS

Hear gives developers 10,000 free transcription minutes every month. Telephony is $0.01/min; Recap is $0.03/min on Omni API and included in Agents; KB Context is $0.003/min.

Free to start
$50

in free credits to start. Plus 10,000 free speech-to-text minutes every month and $5.00/month recurring credit. No card.

Claim your free credits
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 existing OpenAI SDK at https://api.pyai.com/v1 and pass your PyAI key. Transcription and speech use the same request and response shapes, and errors come back in the OpenAI envelope.

How much does it cost?

Hear (transcription) gives you 10,000 minutes free every month; beyond that it's $0.003/min. Omni API is $0.05/min all-in, and managed Omni Agents are $0.08/min. You also start with $50.00 in free credits plus $5.00/month - no card.

Is it good for telephony?

That's the focus. Hear is tuned for 8 kHz call audio, and Omni does end-to-end phone agents with ~431 ms median turn-taking and barge-in.

Do I need a credit card to start?

No. Sign up and your sandbox test key works instantly with free credit. Add funding only when you're ready to send live traffic.

Stop paying for stitched voice AI.

Start with a free key, 10,000 Hear minutes every month, and $50 in credits. Test the same OpenAI-compatible stack you can take to production with Omni, Agents, and Trace.

No credit card - OpenAI-compatible - cancel anytime