Promote Sign in Sign up

Music generation

lyria 3

AI music generator in Gemini using text, image, and video prompts.

Source rating 5.0 (74) 0 views 0 saves Freemium
AI music generation Google DeepMind Lyria 3
More categories (5)
Gemini AI Text-to-Audio Multimodal AI SynthID Audio watermarking
Visit website Sign in to save

Free

Verdict

A quick read before you dig into the full page.

Best if
AI music generator in Gemini using text, image, and video prompts
Skip if
You need enterprise SLAs or a fully managed team plan right away
Pick this when
Freemium · Free

Overview

Lyria 3 is the latest AI music generation model from Google DeepMind, integrated directly into the Gemini app. Launched in February 2026, it represents a significant leap from its predecessors by offering multimodal capabilities, allowing users to generate 30-second music clips using text, images, or video context. The model automates complex musical tasks such as lyric writing and song structuring (including intros, verses, and choruses). It also incorporates SynthID watermarking for audio provenance and safety. While Lyria 3 is the primary consumer-facing tool in Gemini, the Lyria 2 model remains the enterprise standard for developers via Vertex AI API.

lyria 3 screenshot

Access & connections

Where you can use lyria 3.

Platforms

Web

Capabilities

What this tool accepts, produces, and is strongest at.

Highlights

  • Multimodal generation (text, image, and video inputs)
  • Automatic lyric generation from prompt intent
  • End-to-end song structuring (intro, verse, chorus, transitions)
  • SynthID audio watermarking for verification
  • High-fidelity 30-second audio output
  • Integration with YouTube Shorts and Dream Track

FAQ 5

What is Google DeepMind Lyria 3?
Lyria 3 is the latest AI music generation model from Google DeepMind, integrated directly into the Gemini app. Launched in February 2026, it represents a significant leap from its predecessors by offering multimodal capabilities, allowing users to generate 30-second music clips using text, images, or video context. The model automates complex musical tasks such as lyric writing and song structuring (including intros, verses, and choruses). It also incorporates SynthID watermarking for audio provenance and safety. While Lyria 3 is the primary consumer-facing tool in Gemini, the Lyria 2 model remains the enterprise standard for developers via Vertex AI API.
How to use Google DeepMind Lyria 3?
Access Lyria 3 through the Gemini app (available for users 18+). Enter a descriptive text prompt detailing the mood, genre, and instrumentation, or provide visual context like an image or video. Use iterative prompting to refine the generated 30-second track's tempo, vocal tone, and arrangement.
Can I access Lyria 3 via an API today?
Currently, Lyria 3 is available as a consumer experience in Gemini. Enterprise API workflows are still centered on Lyria 2 through Vertex AI (lyria-002).
Does Lyria 3 generate lyrics automatically?
Yes, one of the key upgrades in Lyria 3 is the ability to auto-generate lyrics based on the user's prompt intent.
How long are the music tracks generated by Lyria 3?
The current version in Gemini generates tracks that are approximately 30 seconds long.
lyria 3 Free
Visit website