Gemini can now create AI music

Google launches music generation in its Gemini application via the new Lyria 3 model developed by Google Deepmind. The feature is in beta and lets you create 30-second music tracks based on text prompts and/or uploaded images and videos, the announcement post states.

For example, you can describe a genre, a mood, or even a memory, and Gemini will generate a song and lyrics based on your description. It is also possible to control the style, tempo and type of voices used in the generation, giving you more creative control.

All songs are marked with SynthID, Google’s invisible watermark for AI-generated content. Gemini can also check if audio files were created with Google AI. Google emphasizes that the template is intended for original creation and not for imitation of specific artists.

Lyria 3 is available worldwide in English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese. Users must be over 18 years old. Paid Gemini subscribers benefit from higher usage limits.