Can I run Lyria 3 Pro locally or download the weights?

No. Lyria 3 Pro is API-only through the Gemini API; Google has not released open weights and there is no Hugging Face repository.

What does Lyria 3 Pro cost and what is the context window?

Full-length song generation is priced at $0.08 per song, with a free tier available; the model carries a 1,048,576-token context window, though for music generation that figure is less relevant than the per-song pricing.

How does Lyria 3 Pro differ from the standard Lyria 3?

Lyria 3 Pro is the full-song tier, capable of generating complete tracks with verses, choruses, and bridges; the base Lyria 3 family covers music generation more broadly, but Google has not published a detailed feature comparison between tiers.

Lyria 3 Pro Preview

2642°

#llm #google #vision #audio

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Google | 1,048,576 token context | free to use. Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz stereo audio from text prompts or from images. These models deliver structural coherence, including vocals, timed lyrics, and full instrumental arrangements. Lyria 3 Pro can generate full-length songs with verses, choruses, bridges.

Guides for this model

Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026

Open weights vs open source vs API-only: what you are actually allowed to do

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Lyria 3 Pro Preview is Google's music generation model, available via the Gemini API, that turns text prompts or images into full-length songs at 48kHz stereo. It handles complete song structure — verses, choruses, bridges, vocals, timed lyrics, and full instrumental arrangements. If you need to generate finished, broadcast-ready music rather than short clips, this is the tier to try.

Known for

Full-length songs with verses, choruses, and bridges from a single prompt
48kHz stereo output — higher fidelity than most generative audio tools
Vocals with timed lyrics baked into the generation
Image-to-music: accepts images as input alongside text prompts
Structural coherence across long-form compositions, not just loops

Watch out for

API-only, closed weights — you cannot run this locally or inspect the model.
Full-song generation costs $0.08 per song; free tier exists but production use adds up.
No model card details published; capability limits and content policies are not fully documented.

Best for

Audio

Vision

Prompts to try

Generate a full song

Write and generate a full-length pop song about a road trip taken alone after a breakup. Include two verses, a chorus, a bridge, and an outro. The tone should be bittersweet, the tempo mid-range, and the instrumentation acoustic guitar with light electronic percussion. Include timed lyrics.

Image-to-music

I'm attaching a photograph. Generate a full instrumental piece that matches the mood, colour palette, and atmosphere of the image. Aim for a cinematic feel with orchestral strings and ambient textures. Produce a complete composition with a clear intro, development, and resolution.

Genre experiment

Generate a full song that blends 1970s soul with modern lo-fi hip-hop production. The lyrics should be about insomnia in a city that never goes quiet. Include a verse-chorus-verse-chorus-bridge-chorus structure, lead vocals, and a horn section that drops out during the bridge.

Compare with

Gemini 3.8 Flash
API-only model
1,048,576 token context · $0.83/M input, $4.12/M output
Gemini 3 Flash Preview
API-only model
1,048,576 token context · $0.50/M input, $3.00/M output
Gemini 2.5 Flash Lite
API-only model
1,048,576 token context · $0.10/M input, $0.40/M output
Gemini 3.1 Flash Lite
API-only model
1,048,576 token context · $0.25/M input, $1.50/M output

More text models from google

Questions people ask

Can I run Lyria 3 Pro locally or download the weights?: No. Lyria 3 Pro is API-only through the Gemini API; Google has not released open weights and there is no Hugging Face repository.
What does Lyria 3 Pro cost and what is the context window?: Full-length song generation is priced at $0.08 per song, with a free tier available; the model carries a 1,048,576-token context window, though for music generation that figure is less relevant than the per-song pricing.
How does Lyria 3 Pro differ from the standard Lyria 3?: Lyria 3 Pro is the full-song tier, capable of generating complete tracks with verses, choruses, and bridges; the base Lyria 3 family covers music generation more broadly, but Google has not published a detailed feature comparison between tiers.

Captain's verdict
At eight cents a song with genuine structure and 48kHz stereo output, Lyria 3 Pro is a serious tool for anyone who needs finished music, not just loops.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Qwen3 30B A3B Instruct 2507

AI Models for Image, Video & Text Generation

Lyria 3 Pro Preview is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm google vision audio

Browse by Model Family