lyria-3.5 — AI Audio Model
lyria-3.5
Lyria 3.5 is Google DeepMind’s latest music-generation model, designed to create full-length, structured songs from text prompts and image-based musical inspiration. It can generate music across different genres and moods while giving creators control over elements such as tempo, instrumentation, vocals, lyrics, and song structure. Unlike short music-clip generators, Lyria 3.5 is designed for songs lasting up to a few minutes, with generated MP3 audio at 44.1 kHz stereo and optional lyrics. It also supports multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
Pricing: 11 joules / generation
Output will be displayed here
Fill in the inputs on the left and hit RUN to preview the results.
Examples
Explore different use cases and parameter configurations