Lyria 3.5

What you'll need

• Prompt — The text prompt describing the music you want to generate. Include genre, mood, instrumentation, tempo, vocals, and structure for best results. Lyria 3.5 supports full-length songs up to a few minutes — use timestamps or duration hints in your prompt to control song length, e.g. 'a 2-minute track' or section markers like '[0:00-0:30] Intro:...' / '[0:30-1:00] Verse:...'. Supports English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.

About Lyria 3.5

Lyria 3.5 is Google DeepMind's latest music generation model, and you can generate almost any type of music with it

Lyria 3.5 is an AI music model you can run directly in the Percify playground — fill in the inputs and generate right in your browser, or call it programmatically through the Percify API. Each run returns a ready-to-download audio hosted on our CDN, and credits are only charged for successful results.