That to-do list you meant to tackle? It could be a pop anthem. The sunset photo sitting in your camera roll? Now it has a soundtrack. Google’s Lyria 3, integrated into the Gemini app, brings AI-powered songwriting to everyday users.
The AI music model lets anyone with a phone or browser transform a simple text idea—or even a favorite photo or short video—into a 30-second track complete with vocals, lyrics, instrumentation and ready-to-share cover art.
Here’s how it works:
- Go to the Gemini website or mobile app.
- Prompt to play. Describe a vibe as detailed as you can, like “a nostalgic 90s alternative track about a rainy day in Manila” or “a dreamy lounge beat for study vibes.”
- Visual inspiration. If you don’t know where to start with a text prompt, you can also upload a photo and let Gemini generate a melody that matches the mood of the image.
- Once Gemini delivers your first draft, you can refine the track with additional prompts — adjusting the vocals, boosting the energy, or reshaping the mood until it feels right. Lyria 3 offers more hands-on creative control than previous models, generating original lyrics and allowing users to fine-tune elements such as style, tempo, vocal tone, and overall character.
- Once satisfied, you can download the generated track as a high-quality audio file.
All Lyria 3 music is watermarked with SynthID, an inaudible tag that lets Gemini verify whether audio was AI-created. Google also built in safeguards to avoid imitating specific artists directly.
Lyria 3 is available in the Gemini app for all users 18+ in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese,
