01 What happened
OpenAI makes prompt-to-voice generally available to all API customers, letting developers generate custom synthetic voices for GPT-Live by describing vocal qualities in text without needing a reference or consent recording.
02 Key details
- Prompt-to-voice is generally available to all API customers; voice creation free usage billed at standard GPT-Live rates.
- Prompt-generated voices work only with GPT-Live not supported by Text to Speech, Realtime or Chat Completions APIs
- Organizations can create up to 100 prompt-generated voices; only adult voices allowed; recording-based voices require consent recording; limit of 20 per organization.
03 Why it matters
This update significantly lowers the barrier for creating unique voice personalities AI applications enabling faster prototyping and personalization without the need for studio recordings.
04 Who it matters to
Voice agent developers and voice application developers.
Original source