Lyria 3.5 🧠 Model Paid

What it is

Lyria is Google DeepMind's music generation family. Lyria 3.5 launched in Google Flow Music on 29 July 2026 and reached the Gemini app, AI Studio and the Gemini API in early September 2026. It writes full-length songs a couple of minutes long, with vocals, timed lyrics and arrangement, from text or image prompts. A separate Lyria 3 Clip model makes 30-second loops and previews.

Key features

• Full songs with verses, choruses and bridges
• Custom lyrics with [Verse], [Chorus] and [Bridge] tags, plus timestamped sections
• Control over tempo, key and duration
• Improved vocals, with breath, inflection and emotional range
• MP3 output, with WAV available for Lyria 3.5
• SynthID audio watermark on everything it generates

Where you can use it

The Gemini app, Google Flow Music, Google Vids, AI Studio and the Gemini API. Runway's app lists Lyria 3 Pro and Lyria 3 Clip among its audio models.

Pricing and rights

In the Gemini API, Lyria 3.5 costs $0.08 per full song and has no free tier. Lyria 3 Clip Preview costs $0.04 per 30-second clip. Consumer access comes through Gemini and Google AI plans, whose prices we did not verify here. All output carries an inaudible SynthID watermark. We did not find specific commercial-use terms for songs made in the Gemini app. Check Google's terms before you release tracks.

Who it is for

Creators who want quick songs or beds inside Gemini, and developers who want a cheap per-song music API from a major vendor.

Verdict

Lyria 3.5 is a serious rival to Suno, with a clean API price and built-in provenance. It is newly available outside Flow Music, commercial terms for app-made songs are unclear, and editing tools are more basic than Suno Studio.