Prompt-to-voice for GPT-Live
OpenAI released prompt-to-voice for all API customers, which creates a custom GPT-Live voice from a text description through the API or the voice Playground.
Developers can now describe a voice in text and get a custom voice they can reuse in GPT-Live sessions, using the v1/audio/voices endpoint. Creating a prompt-generated voice is free, and speech generation is billed at regular GPT-Live session rates. The same changelog entry adds nine natural voices in German, French, Hindi, Japanese and Korean.
- Date
- Friday 16 October 2026
- Lab
- OpenAI
- Kind
- feature
- Access
- closed API
- Price
- Voice creation is free; speech uses regular GPT-Live session billing
The nine added natural voices are Nuri, Juni, Flitz (German), Brise, Sillage (French), Nira (Hindi), Harema, Shida (Japanese) and Noeul (Korean).
Sources
This record was not yet confirmed by its sources on 16 October 2026. How we check