# GPT-Live-1 brings full-duplex voice agents to the API at $0.05 per minute OpenAI has released GPT-Live-1 to developers as a $0.05-per-minute front-end voice layer that listens and speaks simultaneously, handles interruptions natively and delegates deeper reasoning or tool work to a separate backend model. The architecture matters as much as the voice quality: developers can replace a chained speech-to-text → LLM → text-to-speech loop with one full-duplex conversational model while keeping their own choice of backend reasoning model, tools and agent harness. - Status: Active - Published: 2026-09-11T22:02:51+12:00 - Updated: 2026-09-11T22:02:51+12:00 - Categories: Artificial Intelligence, AI Models, AI Agents, Inference & APIs - Tags: AI agents, audio AI, OpenAI, voice agents - Canonical HTML: https://beyondthe.news/dossiers/openai-gpt-live-1-full-duplex-voice-api-pricing ## What changed OpenAI launched GPT-Live-1 in the API on September 10, 2026. The model handles incoming and outgoing audio together rather than relying on a conventional speech-to-text, text-model and text-to-speech chain. It can listen while speaking, react to interruptions and acknowledgements, manage silence and background speech, emit transcripts and response text, and support explicit turn detection. Developers can pair the voice layer with a separate backend model or agent harness for reasoning and tool use. OpenAI prices the front-end voice layer at $0.05 per minute and supports browser/server/telephony deployment paths. ## Why it matters Voice-agent engineering has often been an orchestration problem: every transition between transcription, reasoning and synthesis adds latency and creates another place where interruptions, timing or context can go wrong. GPT-Live-1 collapses the conversational front end into one model while keeping expensive reasoning separable. That gives builders a new cost and architecture choice: pay a predictable per-minute voice charge, then route simple or complex work to whatever backend model fits the task. It also makes interruption handling and telephony behavior a model capability rather than entirely application code. ## The voice loop becomes one model GPT-Live-1 jointly processes incoming and outgoing audio, allowing it to react while it is speaking. OpenAI positions this as an alternative to cascaded STT–LLM–TTS systems where each handoff adds latency and brittle state transitions. ## Reasoning can stay behind the voice layer The model can delegate deeper reasoning and tool calls to a separate backend model, including third-party models. Developers therefore do not have to use the same model for natural conversation and expensive planning or tool execution. ## Interruption handling is a core capability GPT-Live-1 is designed to handle pauses, backchannels, self-corrections and users speaking over the agent. It also provides native transcripts, response text, keyword biasing and turn detection for applications that still need explicit conversational boundaries. ## Telephony is part of the launch surface OpenAI explicitly supports phone-call use cases as well as browser and server integrations. That makes the release relevant to customer support, reservations, scheduling and other workflows where full-duplex timing matters more than raw text-model benchmark scores. ## Voice cost is separate from reasoning cost OpenAI lists $0.05 per minute for GPT-Live-1's front-end voice layer. The backend model and tools are additional choices and costs, so teams should model end-to-end cost per successful call rather than treating five cents per minute as the complete agent price. ## Key details - GPT-Live-1 became available in the API on September 10, 2026. - The front-end voice layer costs $0.05 per minute. - It can listen and speak simultaneously and respond to interruptions without a turn-based handoff. - Developers can delegate reasoning and tools to a separate backend model or agent harness. - The API exposes transcripts and response text and supports keyword biasing and turn detection. - OpenAI says the model supports telephony as well as browser/server voice-agent deployments. - OpenAI reports a 30-point Full Duplex Bench improvement over GPT-Realtime-2.1, but the claim is vendor-measured and workload-specific. ## Builder takeaways - Benchmark end-to-end call completion and latency against your current STT–LLM–TTS stack; a lower-complexity architecture is only useful if it also handles your domain vocabulary and tools reliably. - Keep simple conversational handling in the voice layer and route expensive reasoning only when needed so backend token cost does not dominate the per-minute price. - Treat transcripts and tool-side records as the authoritative audit trail for consequential actions; natural speech should not make side effects less inspectable. - Test barge-in, background speech, silence and telephony codecs under real conditions rather than evaluating only clean microphone demos. - Budget the $0.05/minute voice charge separately from backend model, telephony and tool costs. ## What to watch - Independent latency and interruption benchmarks against other realtime voice stacks. - Regional availability, data-residency controls and enterprise retention terms for GPT-Live-1. - Whether OpenAI exposes more low-level controls over turn detection, audio codecs and delegation behavior. - Pricing changes as voice traffic scales and competing full-duplex models enter production APIs. - How custom voice access expands beyond sales-gated eligibility. ## Uncertainties - OpenAI's benchmark and customer results are vendor-provided and may not generalize to every accent, language, noise condition or workflow. - The $0.05-per-minute figure covers the front-end voice layer, not the complete cost of a tool-using or reasoning-heavy agent. - Voice and language availability are still expanding, so product coverage may vary by locale. ## Sources - [Build more natural voice experiences with GPT-Live-1 in the API](https://openai.com/index/introducing-gpt-live-1-in-the-api/) — OpenAI · primary release announcement · 2026-09-10T00:00:00+12:00. Primary source for full-duplex architecture, interruption handling, backend delegation, telephony, benchmark framing, pricing and availability.