Audio, Voice & Music

Lifelike text-to-speech, voice cloning, and dubbing.

Generate full songs with vocals from a text prompt.

Speech-to-text and audio intelligence API for developers.

AI noise cancellation and meeting notes for calls.

Studio-quality AI voiceovers for videos and presentations.

AI voice generation and low-latency voice APIs.

Text-to-speech that reads documents and articles aloud.

AI music generation with fine control over structure.

OpenAI's open-source speech-to-text model.