Solaria 3
Gladia
Speech to textTranscribes a recording into words
- Type
- Proprietary
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — no weights published
Our take
Written Aug 2, 2026Solaria 3 is Gladia's hosted-only speech-to-text model that turns audio into written words. It excels on clean recordings and financial calls but degrades sharply on meetings, podcasts and accented speech.
Pick this for financial calls or clean read-aloud transcription where a low error rate is acceptable, or for European-accented English where it performs notably better than on general accented speech. Skip it if you need to transcribe meetings, podcasts, video, or heavily accented speech, or if you want to self-host or compare prices across providers.
The case for it
- Exceptional accuracy on clean, structured audio: about one word in seventy-six wrong on read-aloud speech, and about one in thirty-seven on financial calls.
- Strong performance on European-accented English, with a gap of roughly 3.8 times in its favour over general accented speech.
The case against it
- Severe degradation on challenging audio: roughly eight times the error rate on recorded meetings and general accented speech compared with clean read-aloud.
- Weak on podcasts and video, at more than five and a half times the error rate of clean speech.
- No available pricing or hosting options in our data, with thin transparency around weights, licence and model details.
How good is it?
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 26th of 74
94.7%
Misses roughly one word in 19, averaged over nine English test sets.
5
Stated by the leaderboard; we do not hold the list itself.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to get it
We hold no priced listing for Solaria 3.
There is no copy to download and no host in our price data, so Gladia 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 Gladia sells.
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- 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
- audio->text
- Catalogue slug
- gladia-solaria-3