Krux
March 31, 2026
Google's Lyria 3 Generates Full Songs From Text and Images
Published: March 31, 2026 at 12:31 AM
Updated: March 31, 2026 at 12:31 AM
100-word summary
Google just added Lyria 3 music generation to its Gemini API, letting you create either 30-second clips or full-length songs from text and image prompts. Both models output high-quality 48kHz stereo audio and handle lyrics better than the previous version. What's new: you can now describe a song with words, upload an image for mood inspiration, and get back broadcast-ready audio in MP3 format. The models are already live in the Gemini app, Google AI Studio, and Vertex AI. Every track gets SynthID watermarking to flag AI-generated content. The obvious use case is cranking out royalty-free podcast intros and social ads without hiring composers or negotiating music licenses.
What happened
Google just added Lyria 3 music generation to its Gemini API, letting you create either 30-second clips or full-length songs from text and image prompts. Both models output high-quality 48kHz stereo audio and handle lyrics better than the previous version. What's new: you can now describe a song with words, upload an image for mood inspiration, and get back broadcast-ready audio in MP3 format. The models are already live in the Gemini app, Google AI Studio, and Vertex AI. Every track gets SynthID watermarking to flag AI-generated content.
Why it matters
The obvious use case is cranking out royalty-free podcast intros and social ads without hiring composers or negotiating music licenses.