Frontier Models

Google Releases Lyria 3.5 Music Model in Gemini App and API

The September 2026 update integrates advanced audio generation capabilities into the Gemini platform, supporting full-length tracks with structural complexity and user controls for style and length.

By Marcus Vance September 5, 2026 3 MIN READ

In a modern technology office environment a person is seated at a large desk made of dark wood the desk holds an open laptop computer with a black frame next to the laptop is a pair of black over ear headphones there is an audio mixing console with numerous physical controls such as knobs sliders and buttons all in shades of gray and black cables connect the mixing console to the laptop a pair of studio monitor speakers sit on either side of the desk a microphone stands on a stand to the left the person is wearing a gray sweater and black pants their right hand is on the mouse and left hand near the keyboard the background shows shelves with books and electronic equipment additional items include a tablet device lying flat on the desk surface the floor has a carpet in neutral tones the walls are painted white with some framed abstract art pieces without any writing the person appears focused on the task of adjusting controls on the audio equipment representing the integration of advanced audio generation capabilities this setup illustrates the use of the music model within the platform allowing for full length tracks the environment includes multiple monitors but the screens are not showing any content with text various cables and connectors are visible in different colors like blue red and yellow the chair is ergonomic with black mesh material on the desk there are also some pens and a notebook but the notebook pages are blank without any marks the overall arrangement suggests a workspace dedicated to audio production and technology integration for music creation using user controls for parameters like style and length the desk surface is smooth and polished reflecting the surrounding objects the laptop has ports on its sides with cables plugged in the headphones have soft ear cushions and a padded headband the mixing console features rows of faders in a linear arrangement the speakers have black grilles covering the drivers the microphone has a cylindrical body mounted on a flexible arm the person has short hair and is sitting upright with elbows resting on the armrests the shelves in the background hold stacked boxes and devices with rounded edges the tablet has a thin bezel and lies next to a wireless mouse the carpet shows a subtle pattern of interlocking shapes the framed art pieces display geometric forms in muted colors the cables snake across the desk in organized bundles the ergonomic chair has adjustable height and lumbar support the pens are arranged in a holder made of metal the blank notebook has a hardcover with a textured finish the entire scene conveys a professional setting for exploring audio generation features through hardware interfaces connected to computing devices the audio mixing console includes multiple input channels with gain controls the studio monitors are positioned at ear level for accurate listening the laptop keyboard is visible with keys in standard layout but no labels shown the person manipulates a dial on the console with precise finger movements the background equipment includes rack mounted units with ventilation slots the tablet screen is dark and powered off the carpet extends under the desk legs the walls have subtle texture from paint application the abstract art avoids any representational forms the cables vary in thickness and flexibility the chair wheels are locked in position the pens have different colored caps but no markings the notebook spine is aligned with the desk edge this detailed physical arrangement grounds the illustration in real world hardware and user interaction with audio tools in a technology workspace focused on music model applications for generating complex tracks via integrated platforms — Illustration: AI Intel Report

Lyria 3.5 is Google's flagship music generation model that generates high-quality 44.1 kHz stereo audio from text prompts or image inputs.

Google made Lyria 3.5 available in the Gemini app and the Gemini API on September 4, 2026.

Release Details and Availability

The model rollout expands access to music generation tools through the Gemini platform.

Google stated that Lyria 3.5 is now available in the Gemini app and the Gemini API.

Users gain the ability to generate music directly in the app interface.

Technical Specifications

Lyria 3.5 generates high-quality 44.1 kHz stereo audio from text prompts or image inputs.

The model is optimized for generating full-length songs with complex structural coherence, including multiple verses, choruses, and bridges.

Maximum track length reaches three minutes with variable song lengths supported.

Key technical specifications for Lyria 3.5
Specification	Detail
Audio Output Quality	44.1 kHz stereo
Maximum Track Length	Up to 3 minutes
Input Methods	Text prompts or image inputs
Song Structure Support	Multiple verses, choruses, and bridges

New Features in the Gemini App

In the Gemini app users can select or describe genres.

Users can choose between vocal or instrumental styles.

New templates allow users to jumpstart creativity for background music or custom birthday tracks.

Users have flexibility to choose short or longer tracks.

Easily select or describe your genre and choose between vocal or instrumental styles
Use new templates to jumpstart your creativity for anything from background music to custom birthday tracks
Choose short or longer tracks

Quality Improvements

Lyria 3.5 delivers improvements in musicality with richer, more complex melodic structures.

Enhanced lyrics provide better prompt adherence and structural awareness.

Improved vocals bring more expression and emotion with greater realism, nuance, and pronunciation.

Our newest music generation model, Lyria 3.5, delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks.Google DeepMind

Creative Control Options

The model offers more control over tempo and duration of outputs.

Users can generate cohesive tracks matching exact project durations.

Market and Stakeholder Implications

The rollout empowers users to craft richer tracks with creative control.

Integration in the Gemini app and API extends music generation to developers and end users.

What's Next

Further expansion may occur in Google Flow Music and related Google products.

The focus stays on delivering higher fidelity music generation through the Gemini ecosystem.

Frequently asked

What is the maximum track length for Lyria 3.5?

Lyria 3.5 supports tracks up to 3 minutes long with variable song lengths.

Where is Lyria 3.5 available?

Lyria 3.5 is available in the Gemini app and the Gemini API as of September 4, 2026.

Sources

Google — Lyria 3.5 is now available in the Gemini app and the Gemini API with options to select genres, styles, and track lengths.
Google — Lyria 3.5 delivers significant advancements across musicality, lyrics, and vocal quality.
Google — Lyria 3.5 generates high-quality, 44.1 kHz stereo audio from text prompts or image inputs and is optimized for full-length songs with complex structural coherence.
Google DeepMind — Lyria 3.5 supports tracks up to 3 minutes long and generates cohesive tracks matching exact durations.