All tasks / Models
Pulse
Smallest.ai's speech-to-text model with emotion and speaker detection in 38 languages.
- Smallest.ai
- Closed
- Released 18 Feb 2026
Where it ranks
- ATranscriptionModels · Cloud · 3.3% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)
Facts
- Vendor
- Smallest.ai
- Family
- Pulse
- Released
- 18 Feb 2026
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.0050 per minute of audio (Artificial Analysis lists $5.00 per 1,000 minutes (Smallest AI Pulse); divided by 1,000.)
- Last verified
- 19 Oct 2026
Price from artificialanalysis.ai, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech to Text: AA-WER Streaming | 5% | Smallest Pulse realtimeAA-WER Streaming index (final transcripts), provider Smallest.ai; embedded value 0.049784 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
| Artificial Analysis Speech to Text: AA-WER v2 (non-streaming) | 3.3% | Smallest AI PulseAA-WER v2 (non-streaming), provider Smallest.ai; embedded value 0.0333 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
| Coval Benchmarks: Speech-to-Text WER (24h window) | 4.8% | smallest / pulseCoval STT benchmark, mean WER over the trailing 24h window (snapshot generation 2610, as_of 2026-10-19T09:38Z), n=912 clips; rank 17 of 31; read from the public API that feeds https://benchmarks.coval.ai. | 19 Oct 2026 | benchmarks-api-6wxgp27p2a-ue.a.run.app |
| Hugging Face Open ASR Leaderboard (English, short-form average WER) | 5.7% | smallestai/pulseAverage WER over the board's default datasets (English short-form, version 17-10-2026); rank 10 of 56; read from the Space's /config table data. | 17 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet.