OpenAI Text-to-Speech API

OpenAI's Text-to-Speech API converts text into natural spoken audio using dedicated TTS and GPT audio models. Developers can select built-in voices, stream output, choose common audio formats, and use instructions with supported models to guide accent, emotional range, intonation, speed, tone, and delivery. The speech endpoint is designed for narration and real-time applications, while eligible customers can create consent-verified custom voices for use in text-to-speech and the Realtime API.