Models / Google/ Lyria 3 Clip Preview

Lyria 3 Clip Preview

Google · released Mar 30, 2026

Input: text and images. Output: text and audio.InputOutput
Type
Proprietary
Input
None held
Output
None held
Cached
None held

We don't hold a list price for this model yet · hosted only — we hold no downloadable copy

Our take

Written Aug 2, 2026

Lyria 3 Clip Preview is Google's unreleased audio generation model that turns text and images into text and audio. It can handle up to one million tokens in a single request, but has no live providers, pricing or measured quality data yet.

Who should pick it

This is not yet usable — no providers are listed and there is no way to run it. Monitor for release if you need long-context audio generation from visual prompts, or if you want a system that handles both text and audio output from mixed inputs. Skip it if you need something now, or if you require benchmark scores, pricing transparency or a download option.

The case for it

  • One-million-token request limit — exceptionally large for an audio generation model.
  • Multimodal design accepts both text and images while producing both text and audio output.

The case against it

  • No verified access path or pricing: zero providers are listed.
  • No measured quality data: no benchmark scores in our data.
00

How good is it?

We hold no score for this model.

We look for every model we track on every board we watch, and none of them has turned up Lyria 3 Clip Preview — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.

The boards we watch →

01

Where to get it

We hold no priced listing for Lyria 3 Clip Preview.

There is no copy to download and no host in our price data, so Google is where to look. We watch OpenRouter, the provider APIs we track and the LiteLLM price set; this version appears in none of them, which is a gap in what we collect rather than a statement about what Google sells.

02

When we formed this view

Dates behind this page

Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Mar 30, 2026AnnouncedLyria 3 Clip Preview announced by Google

Prices last checked 9d ago

What we do not know about this model yet

  • No board we watch has turned up a score, so we hold no quality figures at all.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • We don't hold a list price for this model yet — the gap is ours, not the lab's.
03

Licence and identifiers

What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.

Licence

Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.

Identifiers

Modality record
text+image->text+audio
Catalogue slug
google-lyria-3-clip-preview

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us