AI music and audio tools — Free trial

Converts written scripts, uploaded documents, and spreadsheets into synthesized speech across more than 50 languages. It supports multi-speaker workflows, video dubbing with voice cloning, and direct audio exports in MP3 or WAV formats.

Generates complete vocal and instrumental tracks from text prompts or structured lyrics inside a browser-based workstation. It also provides integrated audio tools to separate stems, edit MIDI notes, and master tracks against reference files.

Generates and edits audio to help creators produce voiceovers, clone voices, and design sound effects. It provides text-to-speech in over 150 languages, automated tools to clean up background noise and stutters, and procedural sound and music generation.