OpenAI released prompt-to-voice for all API customers, letting developers create a custom voice from a text description via the v1/audio/voices API or voice Playground and reuse it in GPT-Live sessions (v1/live/sessions). Creating a prompt-generated voice is free, while speech generation uses regular GPT-Live session billing. Nine natural voices were also added for GPT-Live across German, French, Hindi, Japanese, and Korean.
Read the full story on developers.openai.com
What to doTry the prompt-to-voice endpoints to create custom voices, noting that speech generation is billed under regular GPT-Live session pricing.
- Provider
- OpenAI
- Source
- developers.openai.com
- Models
- GPT Live 1gpt-live-1