Google DeepMind music generation model producing high-fidelity stereo tracks with verse and chorus structure from text or image prompts. Lyria 3.5 adds custom lyrics, timestamp-based structural control and SynthID watermarking on all generated audio. Available through AI Studio, the Gemini API and the Gemini app.
Be the first to rate Lyria. Your feedback helps other users decide.
Similar tools in the same category β compare side-by-side
Sesame builds conversational voice AI β speech models designed to sound like a real person in a live...
Hume works on emotion in voice β both producing expressive speech and reading emotional cues out of ...
Low-latency text-to-speech built for real-time use β voice agents, live translation, anywhere a paus...
Guides and comparisons about audio tools
Murf AI Alternatives in 2026: Top Picks Compared β a practical, up-to-date comparison and buying guide.
Murf AI Pricing in 2026: Is It Worth Paying For? β a practical, up-to-date comparison and buying guide.
ElevenLabs Alternatives in 2026: Top Picks Compared β a practical, up-to-date comparison and buying guide.
ElevenLabs Pricing in 2026: Is It Worth Paying For? β a practical, up-to-date comparison and buying guide.
Descript Alternatives in 2026: Top Picks Compared β a practical, up-to-date comparison and buying guide.