GPT-Live-1 mirrors speaker tone and emotion, with steerable pacing and length

OpenAIDevs · x · 2026-09-11

OpenAI's developer account detailed more GPT-Live-1 capabilities: developers can shape a voice agent's personality with instructions for tone, pacing, and expressiveness. The model can mirror the tone and emotion in a speaker's voice, adapt to their pace, and supports setting language and response length.

Related event: OpenAI launches full-duplex speech model GPT-Live-1 on API(26 posts)→

Original post →

More from Models

Models channel →