OpenAI adds prompt-to-voice and native Decisions to GPT-Live

OpenAI expanded its GPT-Live developer API with prompt-to-voice generation, which creates a reusable voice from a text description without any audio recording, and native Decisions API integration that removes the relay step adding latency to in-session action selection. Nine new voices for German, French, Hindi, Japanese and Korean also arrived. Voice generation is free; speech output is billed at $0.05 per minute.

• Voices are generated via /v1/audio/voices from a text description of accent, tone and pace
• Native Decisions integration cuts latency at in-session action selection
• Nine new voices added for German, French, Hindi, Japanese and Korean
• Speech output costs $0.05 per minute; voice generation is free