WavePrompt is a free app for Mac. Describe a sound and WavePrompt renders it on your Mac. Loops come out cut to exact bars at your tempo, vocal phrases sing your own words, and songs run from intro to outro. The YuE2 music model runs on the Apple Silicon GPU, so prompts, lyrics and audio never leave the machine.

Loops

Bar-accurate loops from 1 to 16 bars at 60 to 180 BPM, in any major or minor key and in 4/4, 3/4, 6/8, 5/4 or 7/8.
Sample-accurate loop starts with nudging, so loops drop straight into a DAW grid.

Vocal phrases

Short sung phrases from your lyrics in English, Chinese, Japanese, Korean, Spanish, French, German, Italian or Portuguese.
Eleven voice types including breathy, powerful, deep, raspy, falsetto, whisper, choir and rap, with optional vocal isolation.

Songs

Full songs from 30 seconds to 4 minutes, with vocals or instrumental, ending on a planned outro.
Lyrics are checked with Whisper and the vocal is fitted over the backing track.

Style

34 genres, 14 moods and 11 instrument sets, plus a style strength setting for how closely the audio follows the prompt.
Shuffle and reset buttons per section, and fixed seeds to repeat or vary a result.

Library and export

Every render is kept in the library with its recipe, and its seed and style can be reused in another type.
Export to WAV (48 kHz, 24-bit) or AAC, with tempo matching by the Rubber Band Library.

Local generation

Generation runs on the Apple GPU through Metal. No server, no account, no upload.
After the first model download, WavePrompt works offline.

Mac

Apple Silicon (M1 or later). Intel Macs are not supported.
16 GB unified memory or more. 32 GB recommended for full songs.
Render time depends on the chip and the number of GPU cores.

Software and storage

macOS 26 Tahoe or later.
About 10 GB of free disk space for the models and the engine.
An internet connection for the first model download only.

Music is generated with YuE2 by Multimodal Art Projection. Model weights are licensed under CC BY-NC 4.0 with individual creator permission, and generated audio is yours to use under that permission. Also uses Demucs, Whisper and the Rubber Band Library.