The fast, low-cost default — instant speech-to-speech reactions with built-in VAD and Krisp noise cancellation.
Reasoning-grade speech-to-speech with steerable, expressive delivery — best when logic and nuance both matter.
Internal reasoning at zero added latency — best for fast-moving, objection-heavy conversations.
Ink STT → GPT-OSS-120B → TTS pipeline with semantic VAD and expressive voice tags for maximum control.
Rates are per connected call-minute · Telnyx carrier fees billed at cost · volume discounts on Enterprise
Pick an engine and drag to your expected volume.
Each engine has its own all-in per-minute rate — no platform fee on top. Gemini Flash Live and the Cartesia cascade are the cheapest per minute; reasoning-grade engines like OpenAI Realtime 2.1 and Grok Think Fast cost more because they spend compute thinking mid-call.
Calls run over Telnyx. Shared numbers are included; Enterprise plans get dedicated numbers and multi-region routing for better answer rates and compliance. Carrier fees are passed through at cost.
Yes. Settings cascade from global defaults to per-campaign overrides, so you can run Gemini on one campaign and OpenAI Realtime 2.1 on another — and audition any voice on a live test call first.
No. It's pure pay-as-you-go — you're only billed for connected call-minutes, and you can stop anytime.