OpenAI TTS

OpenAI TTS converts text into natural-sounding speech using six distinct voices: Alloy, Echo, Fable, Onyx, Nova, and Shimmer.

Integrate the tts-1 or tts-1-hd models to generate studio-quality audio for your applications. You get six optimized voice profiles (Alloy, Echo, Fable, Onyx, Nova, and Shimmer) to fit any brand persona. The system handles 50+ languages and outputs to multiple formats: MP3, Opus, AAC, and FLAC. Use tts-1 for low-latency tasks like live chat or tts-1-hd for premium content creation. It is a direct, reliable solution for adding professional narration to your stack via simple API calls.

https://platform.openai.com/docs/guides/text-to-speech