Smallest AI Pulse
Smallest AI
Speech to textTranscribes a recording into words
- Type
- Closed
- 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 Sep 5, 2026Smallest AI Pulse is a hosted-only speech-to-text model that turns audio into written words across 38 languages. It is unusually accurate on clean recordings, podcasts and meetings, but falls behind on heavily accented speech. No pricing or provider options are currently listed.
Choose this for transcribing clean read-aloud audio, podcasts, video or recorded meetings where its error rates beat most rivals. Consider it if you need 38 languages of coverage, though accuracy outside English is unverified. Skip it if your audio features heavy accents, or if you need confirmed pricing and availability today.
The case for it
- About one word in seventy wrong on clean read-aloud audio — better than most of the 74 models tracked.
- Podcast and video error rate matches the best-in-field, well below the worst performers.
- Meeting-room accuracy beats the median by a comfortable margin.
- 38 languages supported, broader coverage than many transcription models.
The case against it
- Heavily accented speech is its weak spot, trailing most rivals at 10.9% word error rate.
- No current offers listed, so pricing and availability are undisclosed.
- Every accuracy figure is English; nothing we hold measures the other 37 languages.
How good is it?
A speech-to-text model for turning recordings into written text, including speakers with a range of accents.
- turning spoken English into written textOpen ASR WER · 15th of 76
- transcribing speakers with a range of accentsAccented speech · 2nd of 76
TranscriptionTurning speech into text4 of 5Open ASR WER · 15th of 76
95.6%
Misses roughly one word in 23, averaged over nine English test sets.
38
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; the placing beneath each rate is against every model measured on that set.
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.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
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 Smallest AI Pulse.
There is no copy to download and no host in our price data, so Smallest AI 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 Smallest AI sells.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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
We hold no licence row of this model's own. A source states its weights are not published, so the determination that governs it is the one for closed weights, API access only.
Identifiers
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- smallestai-pulse