Lyria 3 by Google Deepmind
Turn any photo or thought into a custom song inside Gemini
Visit website →About
Lyria 3 is Google DeepMind's music generation model, available in the Gemini app in beta. It lets anyone make a 30-second track from a text prompt or an image, turning a photo, a mood, or an idea into a short song complete with vocals and cover art.
The output is generated directly in the Gemini app or website, with no separate music tool needed.
It is aimed at casual users and creators who want to make short, personal music, a birthday song, a track to match a photo, a jingle, without any music production skill, and it also powers music features in Google's other creative tools.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
Lyria 3 made the cut for the zero-friction distribution, not the model itself — it lives inside the Gemini app you probably already have open, so turning a photo into a song is a beta feature away rather than a separate tool and account to set up.
Related tools
- 1 PDF to MP3 Turn PDFs into interactive audiobooks with AI Freemium
- 2 Onepin AI voice production agent fixing names, prices and dates before they ship Freemium
- 3 Whisper The free open-source baseline everyone benchmarks — weak on Gulf dialect Free
- 4 Azure AI Speech 18 Arabic locales, extra tuning for Saudi Arabic, and a UAE region Freemium
- 5 ElevenLabs Scribe Transcription from the voice-AI company, with 32-speaker diarization Freemium
- 6 AssemblyAI Developer speech API that rates its own Arabic honestly: 10-25% error Freemium