Home / Technology / Gemini's New AI Can Now Compose Music From Text
Gemini's New AI Can Now Compose Music From Text
18 Feb
Summary
- Gemini chatbot now generates 30-second audio clips.
- Users can create music from text and image prompts.
- All generated songs include Google's Synth ID watermark.
Google's Gemini chatbot has introduced a new music generation model, Lyria 3, allowing users to create 30-second audio clips using text and visual prompts. This feature, rolling out starting today for users aged 18 and over on desktop, expands Gemini's capabilities beyond image and video generation.
Users can initiate music creation by selecting genres like 90s rap or Latin pop, or by describing specific elements such as mood, tempo, and vocal style. The model can also interpret image prompts to inform the musical theme. All generated songs will feature Google's Synth ID watermark for authenticity and are designed to avoid mimicking existing artists.
Lyria 3 is also being integrated into YouTube's Dream Track tool for Shorts. While free users will have limits, AI Plus, Pro, and Ultra subscribers will enjoy higher usage allowances. This development follows similar AI music generation tools from platforms like Suno and Udio, which have navigated copyright challenges.
