Lyria 3 Pro Preview
VerifiedGoogle's advanced preview model for multimodal audio generation and editing.
About Lyria 3 Pro Preview
Designed as a preview release, Lyria 3 Pro Preview combines multiple input modalities to support detailed audio projects. Its large context capacity enables handling of extended sequences while incorporating visual references and textual instructions. This setup provides fine-grained control during generation and modification tasks.
Strengths include coherent output across long audio durations and effective alignment between sound and accompanying images or prompts. The non-open-weight approach allows Google to deliver regular refinements without user-side deployment concerns. It performs reliably in creative pipelines that demand precision and consistency.
Common uses involve video scoring, custom music composition, sound effect design, and audio remixing. Media professionals apply it to accelerate iteration on soundtracks and effects. Integration with broader Google ecosystems further streamlines production for teams working on multimedia content.
Capabilities
Best for
Long-form Music Composition
Lyria 3 Pro Preview generates extended musical pieces that retain thematic and structural coherence across very long durations thanks to its 1M-token context.
Podcast and Audiobook Sound Design
The model integrates original scores, transitions, and ambient layers into hour-long spoken audio projects while preserving narrative flow.
Film and Game Soundtrack Creation
It aligns music cues precisely with extended video timelines by processing large audio contexts in a single pass.
Strengths & limitations
Strengths
- +Very large context window for extended compositions
- +Native multimodal support across text, image and audio
- +High-quality audio output from Google research
- +Strong integration of visual and textual conditioning
Limitations
- –Preview release may contain inconsistencies
- –Primarily specialized for audio rather than general tasks
- –Resource-intensive due to large context and modalities
Pricing by provider
Live per-provider pricing & uptime, routed via OpenRouter. Prices are USD per 1M tokens.
| Provider | Input /1M | Output /1M | Context | Uptime |
|---|---|---|---|---|
| Google AI Studio | Free | Free | 1049K | — |
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "google/lyria-3-pro-preview",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: google/lyria-3-pro-preview
Editor's verdict
Lyria 3 Pro Preview is Google's proprietary audio & music with a 1049K-token context window.
At no token cost, it is free to run for its class, served by 1 provider.
It is available through Google's API and aggregators like OpenRouter.
Best suited to very large context window for extended compositions and native multimodal support across text, image and audio.
Frequently asked questions
Pricing follows Google's standard audio model usage rates and is listed in the Google Cloud console under the Lyria product page.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Lyria models
Sibling versions in the Lyria family from Google.
Similar models
Other audio & music worth comparing.