Start creating

Lyria 3.5AI music generator

Google's newest music model, from a prompt or an image. On Leap, it sits beside 174 other models in one studio.

  • Music

1 clip on Lyria 3.5: $0.135. Your words wait while you sign in.

  • No subscription
  • Every top model, one account
  • Pay per run, priced before it starts

Listen / Gospel choir and Hammond organ

0 / 60 s

Listen / Synthwave for an empty coastal highway

0 / 60 s

AI music generator

Lyria 3.5 at a glance

Lyria 3.5 is a music model from Google. It makes music from words or a photo.

The version before it: Lyria 3.

Made by
Google
Makes
Music
Starts from
Words or a photo
Prompt
Up to 5,000 characters
Price per run
$0.135
Updated
October 3, 2026
  1. 01Write the words, pick a voice
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Pick the right one

Lyria 3.5 and its siblings

ModelBest forPrice per run
Lyria 3.5 (this page)Google's newest music model, from a prompt or an image.$0.135
Lyria 3Google's Lyria 3: 30-second tracks at a low price.$0.054
Lyria 230-second instrumental clips in high fidelity.$0.135

Start with an idea

Three ways to try Lyria 3.5

Why Leap

Why creators make it on Leap

  1. 01

    Every top model, side by side

    175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.

    See the models
  2. 02

    One click, or full control

    Character Studio, effects and recipes write the prompt for you. Or write your own for any model.

    See the tools
  3. 03

    Your work stays yours

    Everything you make stays in your library while your account is active, and you own what you make here.

    See what people make
  4. 04

    One balance for everything

    The studio, the API and your agents spend the same balance, and every run shows its price before it starts.

    How pricing works

Questions

Lyria 3.5, answered

What is Lyria 3.5?
Lyria 3.5 is a music model from Google. Google's newest music model, from a prompt or an image. On Leap it runs in one studio beside every other top model, with one account.
Can Lyria 3.5 start from a photo?
Yes. Lyria 3.5 starts from words or a photo.
What's new in Lyria 3.5?
Lyria 3.5 follows Lyria 3. A default run costs $0.135, against $0.054 for Lyria 3.
How is it different from Lyria 3 and Lyria 2?
Lyria 3.5: Google's newest music model, from a prompt or an image. Lyria 3: Google's Lyria 3: 30-second tracks at a low price. Lyria 2: 30-second instrumental clips in high fidelity. They all run in the same studio, so you can try one prompt on each.
How much does a run cost?
A track costs $0.135. You see the exact price before you press go, and a run that fails costs nothing.
Is Lyria 3.5 free to try?
No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.135 (a track), so $5 covers 37 of those. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?
Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?
Yes. Leap's REST API runs it as google/lyria-3.5, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a Google account?
No. Leap sends your request to Google's model and gives you what it makes. One Leap account runs Lyria 3.5 and every other model, in the studio, through the API and from your agents.

Your idea, Lyria 3.5.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with Lyria 3.5

For developers

Run Lyria 3.5 from code

Model ID
google/lyria-3.5
Makes
Voice and sound
Pricing
Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Promptprompt
Text, up to 5,000 characters, required
Imageimages
An imageThe uploaded image to work on, by ID.
Negative promptnegative_prompt
Text, up to 2,000 charactersWhat the image should not contain.

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "google/lyria-3.5",    "input": {      "prompt": "A paper boat drifting down a rainy street at dusk"    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"