FULL STORY
OpenAI Launches GPT-Live-1 Voice Model on API
OpenAI brought ChatGPT's natural full-duplex voice experience to developers via the GPT-Live-1 API. Follow-up analysis pegged its $0.05-per-minute pricing at roughly $28 per million tokens.
2026-09-11 ~ 2026-09-12 · 2 episodes · 39 posts
Episode 1 · OpenAI brings full-duplex speech model GPT-Live-1 to its API (2026-09-11, 37 posts)
On September 11, OpenAI officially announced that the speech model GPT-Live-1 is now live on the API, opening up ChatGPT's natural full-duplex conversational experience to developers: voice agents can listen while speaking, support user interruptions and natural back-and-forth, and developers can freely pair the voice interaction frontend with a text model and harness of their choosing. The company says it achieves unprecedented turn-taking naturalness among the most advanced speech models.
Confirmed
- Interruption support: users can add details or change topics mid-utterance without waiting for the model to finish its turn.
- Noise robustness: the model can distinguish speech from background noise; an official demo showed a conversation continuing in a noisy café without breaking off.
- Customizability: developers can use instructions to set a voice agent's tone, pacing, and expressiveness; the model mirrors the emotional tone of the speaker and adapts to their speaking speed, and also supports setting language and response length.
- Architectural flexibility: the speech model can act as an interaction frontend, delegating tasks to a text model of the developer's choice.
Why it matters
- This is the first time OpenAI has exposed ChatGPT's real-time full-duplex voice capability as an API, letting developers build near-human conversational experiences into their own voice agent products with more control over how agents speak and behave.
- Decoupling the voice frontend from the text reasoning backend means developers aren't locked into a single model stack, offering far greater flexibility for building voice agents.
- OpenAI Launches GPT-Live-1 API Bringing Full-Duplex Voice Conversations to Developers — TheMoonMidas · 2026-09-11
- GPT-Live-1 launches in API: SOTA voice model with natural turn-taking and text-model delegation — pbbakkum · 2026-09-11
- OpenAI launches GPT-Live-1 voice model in the API — OpenAIDevs · 2026-09-11
- GPT-Live-1 separates speech from café noise and lets you steer mid-sentence — OpenAIDevs · 2026-09-11
- GPT-Live-1 handles noisy rooms and mid-sentence interruptions for fluid voice chat — OpenAIDevs · 2026-09-11
- OpenAI launches GPT-Live-1: one model for listening and speaking with tunable tone — OpenAIDevs · 2026-09-11
- GPT-Live-1 mirrors speaker tone and emotion, with steerable pacing and length — OpenAIDevs · 2026-09-11
- OpenAI launches GPT-Live voice model; Telnyx ships 16kHz wideband outbound-calling tutorial — OpenAIDevs · 2026-09-11
- OpenAI ships GPT-Live API docs: prompting differs from Realtime series — juberti · 2026-09-11
- OpenAI dev notes GPT-Live-1 API changes and new prompting approach — juberti · 2026-09-11
- OpenAI's GPT-Live-1: full duplex, emotion-matching voice API at 5 cents/minute — pbbakkum · 2026-09-11
- OpenAI launches GPT-Live-1 voice API with full-duplex chat at $0.05/minute — pbbakkum · 2026-09-11
- OpenAI launches GPT-Live-1 voice API; Elise AI deploys it for healthcare calls — pbbakkum · 2026-09-11
- OpenAI's GPT-Live-1 Revealed via Design Partner Elise AI Announcement — OpenAIDevs · 2026-09-11
- OpenAI opens GPT-Live-1 API for voice agents that listen while they speak — paw_lean · 2026-09-11
- OpenAI ships GPT-Live-1 realtime voice API as HeyGen announces integration — HeyGen · 2026-09-11
- OpenAI's GPT-Live-1 Hits the API: Listens While It Talks, Priced at $0.05/Min — Dimillian · 2026-09-11
- OpenAI Publishes Production-Focused Benchmarks for GPT-Live-1 Voice Agents — OpenAIDevs · 2026-09-11
- OpenAI: GPT-Live-1 completes 83.6% of voice-agent tasks first try vs 45.7% for GPT-Realtime-2.1 — OpenAIDevs · 2026-09-11
- OpenAI ships GPT-Live-1 API for voice agents that listen while they speak — jasonkneen · 2026-09-11
Episode 2 · GPT-Live costs ~$28/M tokens, hands off reasoning to backend models (2026-09-12, 2 posts)
GPT-Live charges $0.05/minute, which works out to roughly $28/M tokens assuming 12.5Hz audio tokens. Unlike GPT-Realtime, it only handles conversation while delegating reasoning and tool calls to backend models.
- GPT-Live handles only conversation, delegating reasoning and tools to a backend model — rdesh26 · 2026-09-12
- GPT-Live's $0.05/min pricing works out to ~$28/M tokens, hints at mid-size frontend model — rdesh26 · 2026-09-12