whatmodel.sh / stt / Cactus Whistle

Cactus Whistle

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Cactus Whistle is an open-weights speech-to-text model from Cactus Compute, released October 2026. Licence: apache-2.0.

Catalogue identity notes

Pinned public model card and documented runtime. No measured runtime memory requirement verified; model file size is not labelled as RAM.

Model information sources

Release date ↗

No comparable score yet. Its published results are below, but they don't overlap enough with other models to calculate a score.

$ how it compares

Scored speech-to-text models released closest to Cactus Whistle, out of 178 with a score.

#modelscorewhereRAMreleased
1Muse Voice Transcribe 1.0 Meta71±3api $0.0030/audio min2026-09
2Grok Voice Transcribe 2.0 xAI70±3api $0.0017/audio min2026-09
4Universal-3.6 Pro Realtime AssemblyAI70±3api $0.0075/audio min2026-09
5Linden 1 (Agent STT) Speechmatics69±3api $0.0050/audio min2026-09
24Qwen-Audio-3.0-ASR Alibaba62±4comparison only2026-09

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 0.0% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER lab4.3% ✎▁·▁·▁▁▃▁▃▇█▆ beats 10/102—not counted yet: no other model in the same run to compare it with
LibriSpeech test-other WER lab10.5% ✎▁···▃▁▁▆▆█▆▁ beats 2/56—not counted yet: no other model in the same run to compare it with

$ where to run it

No verified API or download recorded yet · add one

Official weights and documentation: huggingface.co/Cactus-Compute ↗

$ published results · 2 results, not enough overlap for a score
testresultsource and conditions
LibriSpeech test-clean WER4.3%Cactus Whistle model card · lab-reported

Own labelled SVG figures; full LibriSpeech test sets, Whisper normalization, native 2–4 bit C++ runtime, 5 beams; copied competitor bars excluded.

LibriSpeech test-other WER10.5%Cactus Whistle model card · lab-reported

Own labelled SVG figures; full LibriSpeech test sets, Whisper normalization, native 2–4 bit C++ runtime, 5 beams; copied competitor bars excluded.

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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