Lyria 3 Clip Preview
Google · released Mar 30, 2026
- 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, 2026Lyria 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.
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.
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.
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.
When we formed this view
Dates behind this page
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.
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