Lyria 3 Pro 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 Jul 28, 2026Google's preview audio-generation model can turn text and images into both text and spoken audio, with an unusually long context window of about one million tokens. It is not yet available through any commercial service.
Wait for this if you need long-context audio generation or multimodal pipelines that produce synchronized text and audio from visual prompts. Skip it entirely if you need something deployable today, as there is no API access, no pricing and no confirmed release timeline.
The case for it
- Context window of 1,048,576 tokens — roughly four times longer than typical audio models.
- Rare multimodal pairing: text and audio output from text and image input.
- Recent preview from a major vendor, released March 2026.
The case against it
- No commercial availability: zero offers, no pricing and no way to deploy.
- No measured performance data: no benchmark scores have been published.
- Proprietary weights with no open licence, so self-hosting will not be an option if it does launch.
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 Pro 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 Pro 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-pro-preview