OpenAI made several GPT-Live updates to its API on October 15 and 16, 2026, according to its developer changelog.
What to know
- Prompt-to-voice (October 16): released for all API customers. You can create a custom voice from a text description through the API or the voice Playground, then reuse it in GPT-Live sessions. OpenAI says creating a prompt-generated voice is free, and speech generation uses regular GPT-Live session billing.
- Nine new voices (October 16): Nuri, Juni and Flitz in German; Brise and Sillage in French; Nira in Hindi; Harema and Shida in Japanese; and Noeul in Korean.
- Decisions integration (October 15): GPT-Live can call Decisions directly, so an app can act while the user is speaking or react to what Live says. The changelog lists it for
gpt-live-1andgpt-6-luna.
Why it matters
Creators and developers who build voice apps now have a way to describe a voice in words instead of picking from a fixed list. It sits alongside other voice launches such as Eleven v4 from ElevenLabs. These are OpenAI’s own descriptions; try the voices with your own scripts before choosing. See our AI voice prompt ideas.
Source: OpenAI API changelog. We summarise in our own words; check the source for the full details.