OpenAI API: design a custom voice from a text prompt, plus nine new GPT-Live voices
Prompt-to-voice is now available to all API customers: describe a voice in words, then reuse it in GPT-Live sessions. Creating the voice is free.
As of Oct 16, any OpenAI API customer can create a custom voice from a text description, either through the API or in the voice Playground, and reuse it in GPT-Live sessions.
- Creating a prompt-generated voice is free. Speech generation is billed at regular GPT-Live session rates.
- Nine new voices were added: Nuri, Juni and Flitz (German); Brise and Sillage (French); Nira (Hindi); Harema and Shida (Japanese); and Noeul (Korean).
A day earlier (Oct 15), OpenAI also added native Decisions integration to GPT-Live, so apps can act while the user is still speaking.
Why it matters
Voice apps can get a distinct branded voice without recording sessions or licensing a voice actor. You pay only normal GPT-Live session billing when it speaks.