Google adds music-generation capabilities to the Gemini app
Source: TechCrunch
Google adds music‑generation capabilities to the Gemini app
Google announced that the Gemini app will now include a music‑generation feature powered by DeepMind’s Lyria 3 model, currently in beta.
How the feature works
- Describe the song you want, and Gemini generates a short track (e.g., a 30‑second “comical R&B slow jam about a sock finding its match”) along with lyrics and cover art created by Nano Banana.
- You can also upload a photo or video, and the AI will compose music that matches the mood of the media file.
Improvements with Lyria 3
Lyria 3 builds on the previous generation of models, delivering more realistic and complex music tracks. Users can control elements such as style, vocals, and tempo.
Read about the earlier generation of models.
Availability
- Gemini app: Rolling out to all users aged 18+ worldwide, supporting English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
- YouTube Dream Track: The model is also being made available to YouTube creators via the Dream Track feature, expanding from a U.S.-only beta to global access.
- More info on Dream Track: YouTube support page.
Artist‑style prompts and safeguards
Google states that the system is designed for original expression, not for directly mimicking existing artists. If an artist’s name appears in the prompt, Gemini treats it as broad creative inspiration and generates a track with a similar style or mood.
“Music generation with Lyria 3 is designed for original expression, not for mimicking existing artists. If your prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood. We also have filters in place to check outputs against existing content.”
— Google blog post
SynthID watermark and detection
All songs created with Lyria 3 carry a SynthID watermark to identify AI‑generated content. Gemini will also include tools to let users upload a track and ask whether it was AI‑generated.
- Details on SynthID detection: Google support page.
Industry context
AI‑generated music has sparked mixed reactions:
- Adoption: Platforms like YouTube and Spotify are integrating AI music and signing deals with labels to monetize it.
- Legal challenges: Music‑industry lawsuits claim AI models infringe on copyrights of training data.
- Transparency tools: Services such as Deezer have introduced mechanisms to label AI‑generated tracks and curb fraudulent streaming.
- See Deezer’s approach: TechCrunch article.