whatmodel.sh / stt / Speechmatics Enhanced
Speechmatics Enhanced
↗ share
+ contribute
Speechmatics Enhanced is a closed-weights speech-to-text model from Speechmatics, released March 2023. Licence: proprietary.
Score within the Open ASR English short-form WER (March 2026) comparison set only.
$ how it compares
The speech-to-text models ranked either side of Speechmatics Enhanced, out of 176 with a score, then more from Speechmatics.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 40 |  Canary-1B-Flash | 60±2 | local | ||
| 41 |  Granite Speech 3.3 2B | 60±3 | local | ||
| 42 | Speechmatics Enhanced | 60±2 | api $0.0067/audio min | ||
| 43 |  Deepgram Nova 2 | 60±4 | api $0.0058/audio min | ||
| 44 |  Fun-ASR-Flash | 59±4 | comparison only | ||
| more from Speechmatics | |||||
| 5 | Linden 1 (Agent STT) | 69±3 | api $0.0050/audio min | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
long-form transcription▁▁▄▁·▁▂█▄▁▃▁ #2 of 27 * · 13% of its score · 1 test
Beats Cohere Transcribe (03-2026), Canary-Qwen-2.5B, Chirp 3 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR English long-form WER | 7.0% ✎ | ▁▁▅▁·▃▅█▆▁▃▂ beats 27/30 | 13% |
multilingual transcription▂··▃▄█▆▅▄▂·▂ #8 of 36 * · 44% of its score · 1 test
Beats Cohere Transcribe Arabic (07-2026), Nova-3, Qwen3-ASR-1.7B here, though they rank higher overall. Trails SeamlessM4T v2 Large, Whisper large-v3 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR multilingual WER | 4.3% ✎ | ▂··▂▃▂█▃█▂▁▁ beats 25/29 | 44% |
other tests6 not in a task · 41% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR English short-form WER (March 2026) | 6.9% ✎ | ▁▁▁▃··▁▁▂██▆ beats 62/86 | 13% |
| RW-Voice-EQ ASR · 4 real-world English sets, mean WER | 9.0% ✎ | █▃▃▅▃···▃··▃ beats 4/9 | 10% |
| verli STT benchmark · LibriSpeech test-clean WER | 2.2% ✎ | ▃·····▃▅█▃▅▅ beats 3/11 | 7.8% |
| verli STT benchmark · SPGISpeech 1,200-clip sample WER | 3.0% ✎ | ▂·····▄▂█▂▂▄ beats 6/11 | 3.7% |
| verli STT benchmark · Earnings-22 WER (2,741 utt.) | 12.3% ✎ | ▃·▃▅··▃▃▅▅█▃ beats 5/13 | 3.4% |
| Quranic ASR Leaderboard · held-out recitation (600 clips) overall WER | 19.5% ✎ | ▃·▅·▅▃▃·▃▃▃█ beats 6/12 | 2.4% |
$ where to run it
Through an API
api · $0.0067/audio min · www.speechmatics.com ↗ · price sourceUSD per input audio minute: Speechmatics Pro plan (no commitment) lists Batch Enhanced at $0.40/hr (÷60). Product: Speechmatics batch speech-to-text. API model: enhanced operating point. Settings: Pro plan, batch. Price basis: published list rate, per-hour to per-minute scaling only. Exclusions: 20% volume discount over 500 hr/month, real-time Enhanced ($0.43/hr), bolt-ons. Currency: USD. Speechmatics official pricing page, observed 2026-09-25.
$ how the score was worked out · Open ASR Leaderboard 71%, verliapp/stt-benchmark · inde… 15%, RW-Voice-EQ Bench (Hume AI) 10% and 1 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Open ASR Leaderboard | 3 | 71% |
| verliapp/stt-benchmark · independent STT accuracy benchmark | 3 | 15% |
 RW-Voice-EQ Bench (Hume AI) | 1 | 10% |
| Quranic ASR Leaderboard (Quran-Lab, held-out recitation set) | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 59.7 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json