OpenAI has made voice creation from text descriptions available to all API customers
All API customers can use the prompt-to-voice feature to create a custom voice from a text description and reuse it in GPT-Live sessions. Creating a voice is free, while speech generation is billed under the standard GPT-Live terms.
OpenAI has made the prompt-to-voice feature available to all API customers. A custom voice can be created from a text description through the API or in voice Playground, then reused in GPT-Live sessions. The announcement applies to the model gpt-live-1.
According to OpenAI, creating a voice is free; speech generation is subject to standard billing for GPT-Live sessions. Nine voices have also been added: Nuri, Juni and Flitz for German, Brise and Sillage for French, Nira for Hindi, Harema and Shida for Japanese, and Noeul for Korean.
Why it matters
Developers can try out different voice designs without paying to create them and use their chosen voice in subsequent sessions. When estimating the operating costs of a voice application, however, they must still account for charges for generated speech.
Two audiences, two different impacts
What this means
For individuals
An API customer can create a custom voice directly in voice Playground, trying out voice design through text without setting up an API integration.
For a business
A company can reuse a voice in GPT-Live sessions once it has been created. The budget for a voice application must still include speech generation, even though creating the voice itself is free.
DevelopmentCheck the original
Event sources
clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.