Models / Smallest AI/ Smallest AI Pulse

Smallest AI Pulse

Smallest AI

Speech to textTranscribes a recording into words

Input: audio. Output: text.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 — no weights published

Our take

Written Aug 2, 2026

Smallest AI Pulse is a hosted-only speech-to-text model that turns audio into written words across 38 claimed languages. It excels on clean, scripted audio with very low error rates, but performance falls sharply on meetings, podcasts and accented speech.

Who should pick it

Choose this for high-stakes transcription of clean, scripted audio where a 1.3% word error rate is acceptable, or for financial calls and European-accented speech where it also scores well. Skip it if you need to transcribe meetings, podcasts, video or heavily accented speech, where its error rate rises more than sixfold, or if you require local hosting or confirmed availability through a provider.

The case for it

  • Excellent on clean, structured audio: about one word in seventy-five wrong on clean read speech, and similarly strong on financial calls.
  • European-accented speech at roughly one word in twenty-six wrong — notably better than its performance on general accented speech.
  • 38 languages claimed, which is broader coverage than many transcription models.

The case against it

  • Performance collapses on real-world, unscripted audio: recorded meetings and podcasts see error rates six to seven times higher than clean read speech.
  • Severe degradation on accented speech: more than eight times the error rate it manages on clean speech.
  • No commercial access path in our data: zero offers, no pricing available, and speed claims are unverified.
00

How good is it?

TranscriptionTurning speech into text3.5 of 5Open ASR WER · 28th of 74

Words it gets right

94.6%

Misses roughly one word in 18, averaged over nine English test sets.

Languages

38

Stated by the leaderboard; we do not hold the list itself.

Where it struggles
Read aloudaudiobooks, clean recording1.3%
Podcasts and videoeveryday internet audio8.2%
Accented speechspeakers from many countries10.9%
Meetingsa room, several people, far microphone9.1%

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.

Also scored, on boards we give no mark for
Financial calls 15th of 74Harder read speech 23rd of 74Recorded meetings 28th of 74Clean read speech 30th of 74Podcasts and video 33rd of 74Accented speech 38th of 74European-accented speech 40th of 74

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.
5.4independentsource ↗
10.9independentsource ↗
1.9independentsource ↗
9.1independentsource ↗
8.2independentsource ↗
1.3independentsource ↗
2.7independentsource ↗
01

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.

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 10.9 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 1.9 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 9.1 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 3.9 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 8.2 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.3 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 2.7 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 5.4 on Open ASR WERleaderboard

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.
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
audio->text
Catalogue slug
smallestai-pulse

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us