Audio: Voice, Music & SFX

Google Lyria 3.5 (Gemini, Flow Music)

Google's Lyria 3.5 music model: make tracks with or without vocals in the Gemini app, Flow Music, AI Studio and Google Vids.

Visit Google Lyria 3.5 (Gemini, Flow Music) (opens in a new tab)

No affiliate links and no sponsorship on this page. Our disclosure policy.

Best for
Beginners and Pro users
Free plan
Not confirmed
Agent-ready (MCP / API)
Partly
Platforms
Web, iOS, Android, API
Last verified
Oct 15, 2026

Summary

Overview

Lyria is Google’s music generation model. Google’s September 2026 announcement describes Lyria 3.5 as its best-sounding music model, with more expressive vocals and richer arrangements. It is available in the Gemini app, Google Flow Music, Google AI Studio and Google Vids, and developers can call it through the Gemini API.

Who it fits

It suits marketers and video makers who need a backing track, brand jingle or background music without licensing a library track. In the Gemini app you pick a genre, choose vocal or instrumental, and start from templates. Google’s ProducerAI, a Labs product, also builds on Lyria for more guided songwriting.

What the plans include

Google says Lyria 3.5 is available to all Gemini app users globally, but limits depend on plan and can change. The API is billed per use; see Google’s pricing page.

Limits and alternatives

Everything is steered by prompts, so detailed arrangement control is limited, and outputs include a SynthID watermark. Suno makes full songs with vocals and has paid commercial plans, Udio offers credit plans, and Stable Audio focuses on instrumentals and sound design.

Who it's for

A good fit if you are…

  • Marketers and video makers who want a custom backing track, jingle or background music from a prompt
  • Developers who want a music-generation model in the Gemini API

Another tool may suit you better if you are…

  • Anyone who needs fixed free limits: Google changes Gemini limits often
  • Producers who want stem-level or DAW-style control

Pricing

Lyria 3.5 is available to Gemini app users worldwide; usage limits vary by plan and the Gemini API is billed per use. Pricing varies, see the official pages. As of Oct 2026, verify.

  • Google's September 4, 2026 announcement says Lyria 3.5 is available to all Gemini app users globally on web and mobile, and in Flow Music, Google AI Studio and Google Vids.
  • Gemini app limits depend on your plan and can change; check Google's Gemini help pages.
  • API pricing is listed on the Gemini API pricing page.

Prices as of Oct 2026 (checked Oct 15, 2026), verify before buying. Source: vendor pricing page.

Key features

  • Tracks from text or image prompts
  • Choose vocal or instrumental styles, genre and track length in the Gemini app
  • Templates for background music, jingles and custom tracks
  • 44.1 kHz stereo audio output (Gemini API)
  • SynthID watermark on outputs from Google's music tools

Integrations: Gemini app, Google Flow Music, Google AI Studio, the Gemini API and Google Vids; ProducerAI in Google Labs also builds on Lyria.

Agent-ready? Partly. Lyria 3.5 is available through the Gemini API (model code lyria-3.5), so apps and agents can call it. No MCP server was confirmed.

Pros and good to know

Drawn from the vendor's own documentation and public sources.

Pros

  • Available inside the Gemini app and Vids
  • Vocal and instrumental options
  • Developer access through the Gemini API

Good to know

  • Gemini app limits change over time
  • Prompt-driven, so less fine control than a music workstation
  • Output carries a SynthID watermark

Alternatives

  • Suno: AI music generator that makes full songs with vocals from a prompt; commercial rights on paid plans, Suno Studio on Premier.
  • Udio: AI music generator with free and paid credit plans; downloads were disabled after its Universal Music Group partnership.
  • Stable Audio: Stability AI's text-to-audio model for music and sound effects, with an API and a commercial licence.

Sources

Spotted a mistake or out-of-date price? We want to fix it, see About for how to reach us.