Build more natural voice experiences with GPT‑Live‑1 in the API
- ID
- 23241
- Status
- summarized
- Published
- 10 Sep 2026, 8:00 AM
- Fetched
- 11 Sep 2026, 1:30 AM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/introducing-gpt-live-1-in-the-api
- Source URL
- https://openai.com/news/rss.xml
Summary
- Score
- 7.0
- Created
- 11 Sep 2026, 1:33 AM
- Tags
- Audience
- developersai_agent_userssaas_founders
What happened
OpenAI launched GPT-Live-1 in the API, a full-duplex voice model that listens and speaks simultaneously, replacing chained STT-LLM-TTS architectures with a single model that reasons over incoming and outgoing audio together. It supports interruption handling (Speak reported ~80% fewer interruptions vs. turn-based systems), delegates reasoning and tool calls to backend models like GPT-6 Astra, and includes telephony support for phone-based agents.
Why it matters
If you are building or planning voice agents, GPT-Live-1 lets you drop brittle STT→LLM→TTS pipelines in favor of a single API call with native interruption handling and background-noise resilience. The telephony support means you can deploy full-duplex agents for phone-based customer support or reservations without stitching together separate telephony and transcription infrastructure.
Discussion angle
Compare GPT-Live-1's single-model approach against existing STT-LLM-TTS stacks on cost, latency, and control — and whether the loss of per-component swapability (e.g., choosing your own TTS voice provider) is worth the reliability gain.