OpenAI ships GPT-Live-1 in the API: one model reasons across audio, no more STT-LLM-TTS chaining
pbbakkum · x · 2026-09-11
OpenAI shipped GPT-Live-1 in the API. Peter Bakkum, MTS on the realtime APIs, explains the shift: instead of chaining separate speech-to-text, LLM, and text-to-speech models, GPT-Live-1 reasons across incoming and outgoing audio as one continuous interaction. That matters because VAD and turn detection have plagued voice agents with awkward pauses, interruptions, dropped context, and false responses to background noise. The model is built around a fluid, turnless interaction model, and alpha testers report conversations that feel far closer to talking with a person. Several developers argue GPT-Live in the API is a bigger deal than Gemini Astra for voice agent integrations.
More from Models
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude — Angaisb_ · 2026-10-27
- Artificial Analysis breaks down all sub-evaluations in Intelligence Index v4.3.2 — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra gains ~20 points on Terminal-Bench 4.0, rivalling GPT-6.1 Sol — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra cuts hallucination rate by 50 points while lifting accuracy 2 points — ArtificialAnlys · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27