GPT-Live prompt-to-voice is GA: describe a voice in text, plus a new Korean voice, Noeul
What is it?
Write a description like "a calm, warm support-agent voice" and the API creates and saves that voice. No reference recording or consent recording is needed. You create it through the API or the voice Playground and reuse it in sessions with GPT-Live, OpenAI's real-time voice model. Creating a voice is free, and speech is billed at normal GPT-Live session rates. The same day, GPT-Live gained nine voices, including Noeul for Korean.
curl https://api.openai.com/v1/audio/voices \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"type": "prompt", "name": "Support assistant", "prompt": "A calm, warm adult voice for a customer support assistant.", "model": "auto"}'Why does it matter?
If you're building a support bot or voice assistant, you can try out an on-brand voice in minutes without booking a recording session. The new Korean voice also makes GPT-Live easier to test for Korean-language products. The catch is that prompt-generated voices only work in GPT-Live. The Text to Speech, Realtime, and Chat Completions APIs can't use them.
Maturity
GAGenerally available to all API customers. Children's voices and impersonating real people are not allowed, and listeners must be told the speech is AI-generated.
How to track it
- API rollout: watch the OpenAI API changelog for GPT-Live-1.1, which reached ChatGPT first.
- Support: check the Custom voices guide for whether prompt-generated voices come to the Text to Speech or Realtime APIs.
- Quality: run the Korean voice Noeul through a real call script and listen for pronunciation and intonation.