LLM Reference
Google AI Studio

Using Lyria 3.5 Pro Preview on Google AI Studio

Implementation guide · Lyria · Google DeepMind

Serverless

Google AI Studio exposes Lyria 3.5 Pro Preview through model ID lyria-3.5-pro-preview. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-03. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Google AI Studio and generate an API key.
  2. 2
    Use the Google AI Studio SDK or REST API to call lyria-3.5-pro-preview — see the documentation for request format.

Code Examples

Install
pip install google-genai
API key
GOOGLE_API_KEY
Model ID
lyria-3.5-pro-preview

Use the model name directly, e.g. "gemini-2.0-flash", "gemini-1.5-pro", or "gemini-2.5-pro-preview-05-06".

import os
from google import genai

client = genai.Client(api_key=os.environ["GOOGLE_API_KEY"])
response = client.models.generate_content(
    model="lyria-3.5-pro-preview",
    contents="Hello"
)
print(response.text)

Pricing on Google AI Studio

Capabilities

VisionMultimodalAudio

About Lyria 3.5 Pro Preview

Lyria 3.5 Pro Preview is Google DeepMind's public-preview full-song music generation model, released in the Gemini API on September 3, 2026. Official model ID lyria-3.5-pro-preview. It accepts text and image input and returns 44.1 kHz stereo audio (MP3) plus lyrics text, with a 131,072-token input limit. First-party positions Pro for full-length songs with verses, choruses, and bridges (DeepMind hub: up to 3 minutes; prompt-controllable duration). Paid Gemini Developer API list price is $0.08 per song; Free Tier is not available. Preview models may change before becoming stable and have more restrictive rate limits.

Model Specs

Released2026-09-03
Context131k