Text-to-music generation
Describe a mood, genre or instrument set and it generates a music track from that prompt, no separate composer or DAW required.
One workspace that generates and edits AI music and sound from a text prompt, covering text-to-music, remix and track editing.
It's the platform's dedicated workspace for sound — generating a track from a prompt, remixing one you already have, and editing the result.
Describe a mood, genre or instrument set and it generates a music track from that prompt, no separate composer or DAW required.
Feed in a track you already have and remix it into a new arrangement, using the remix-capable models to reinterpret rather than start from silence.
Beyond generation, it includes dedicated audio-editing models for cleaning up, adjusting or reshaping a track after it's made.
All 15+ models cover three jobs — generating a track, remixing one, and editing what comes out.
The same flow whether you're generating a track from scratch or reworking one you already have.
Write a text prompt describing the mood, genre or instruments you want, or upload an existing clip to remix or edit.
Choose text-to-music to generate from scratch, or a remix / audio-editing model to work from what you already have.
Preview the result in the studio and download it, or pair it with a Video Studio or Cinema Studio clip for a finished scene.
This is one of 14 purpose-built workspaces on the platform. Here's where to go next.
Turn a still into motion, or generate a clip straight from text — 85+ text-to-video and 120+ image-to-video models.
Generate from a blank prompt or edit an uploaded photo — 70+ text-to-image and 70+ image-to-image models.
Animate a portrait you made here, or re-sync lips on an existing video — 9 dedicated models.
Chain this studio's output into video and audio models as one repeatable, node-based pipeline.
15+ models covering text-to-music, remix and track editing. No subscription, no account required to try it.
Try Free