Skip to content
Products

Omni runs the whole call. The rest are building blocks.

Omni is one speech-to-speech model for telephony agents. Agents Beta, Trace, and Cast carry the rest of production voice work; Hear, Speak, and Telephony are the individual APIs underneath. Start with a sandbox key that never bills.

Live

Omni

The definitive all-in-one AI voice agent model. Hybrid speech-to-speech, fused LLM brain, emotion-aware voices, and tool calling.

Hybrid speech-to-speechFused LLM brainTool / function calling
$0.05/minExplore
Beta

Agents

Launch and manage AI voice agents without code.

No-code builderEvals + monitoringRecap add-on
$0.08/minExplore
Live

Cast

Cinematic, emotional long-form TTS for podcasts, narration, and audiobooks.

Predictable long-form pricingCommercial rights includedVoice Designer (free)
$0.02/minExplore
Live

Trace

Bulletproof compliance & QA on every single call, automatically.

Rule packs: TCPA - HIPAA - PII - brand-voicePASS/WARN/FAIL scorecardsFindings cite the regulation
$0.03/minExplore

APIs and add-ons

Live

Hear

Hear - speech-to-text (STT), telephony-native.

Telephony 8 kHzStreaming partialsWhisper-compatible
$0.001/minExplore
Live

Speak

Speak - text-to-speech (TTS) that starts in milliseconds.

~53 ms warm TTFB (in-region)144 stock voicesVoice cloning (free)
$0.04/minExplore
Live

Cue

Telephony-grade hearing & turn detection - bring your own LLM and voice.

Telephony turn detection (8 kHz)Eager endpointingStreaming
$0.015/minExplore
Beta

Telephony

One agent stack across the PyAI network.

Managed numbers: US + IndiaAutomatic network routingRegional coverage
$0.01/minExplore
Live

AMD

Know who answered. Even when it's an AI screening the call.

iPhone / Google call screeningTen outcome classes, not threeNever drops a live human
$0.004/minExplore
Add-on

Recap

Transform every call into instant, structured intelligence.

Summaries + dispositionsNext stepsCRM-ready fields
$0.02/minExplore
Get a free key
ModelWhat it doesEndpointPriceStatus
OmniThe definitive all-in-one AI voice agent model. Hybrid speech-to-speech, fused LLM brain, emotion-aware voices, and tool calling.wss://api.pyai.com/v1/omni$0.05/minLive
AgentsLaunch and manage AI voice agents without code.Console + wss://api.pyai.com/v1/omni$0.08/minBeta
CastCinematic, emotional long-form TTS for podcasts, narration, and audiobooks.POST /v1/audio/speech$0.02/minLive
TraceBulletproof compliance & QA on every single call, automatically.GET /v1/trace/interactions$0.03/minLive
HearHear - speech-to-text (STT), telephony-native.POST /v1/audio/transcriptions$0.001/minLive
SpeakSpeak - text-to-speech (TTS) that starts in milliseconds.POST /v1/audio/speech$0.04/minLive
CueTelephony-grade hearing & turn detection - bring your own LLM and voice.wss://api.pyai.com/v1/audio/transcriptions/stream$0.015/minLive
TelephonyOne agent stack across the PyAI network.POST /v1/telephony/numbers$0.01/minBeta
AMDKnow who answered. Even when it's an AI screening the call.wss://api.pyai.com/v1/amd/stream$0.004/minLive
RecapTransform every call into instant, structured intelligence.GET /v1/recap/calls$0.02/minAdd-on
Add-ons:Trace ($0.03/min)Recap ($0.02/min)KB Context ($0.003/min) - Full pricing

Choose how you want to start.

Use an instant sandbox key for the API, or open Agents Beta and build without code. Sandbox usage never bills. Live keys require available credit.

Build with the API Launch an Agent

Agents is live in beta. Sandbox keys have daily limits and never touch billing.