← Speech to text (English) libraries · Reader board

Vosk 0.3.45 on Speech to text (English)

130 files: text from 129, empty 1, errors 0, hangs 0, crashes 0. 130 files give text to at least one library.

🔴 Fails where another library reads text: none

🟡 Empty where another library reads text: 1

ami-far-field/AMI_EN2002c_sdm_MEE071_0048700_0048948.wav

no text (0.274 s)

⚔️ Compare: Vosk vs Whisper · faster-whisper vs Vosk

Changes between versions

Only one version tested so far. The next PyPI release is tested automatically.

Badge

For a README: badge

[![Reader board](https://img.shields.io/endpoint?url=https://prometheus-maker.github.io/reader-board/badges/speech-vosk.json)](https://prometheus-maker.github.io/reader-board/speech-vosk.html)

Slowest files

earnings-calls/457_12_45.wav	3.137 s, 261 MB
earnings-calls/735_10_43.wav	2.718 s, 262 MB
earnings-calls/413_2_1.wav	2.48 s, 252 MB
earnings-calls/28_8_25.wav	2.471 s, 252 MB
earnings-calls/161_2_19.wav	2.391 s, 249 MB
earnings-calls/328_1_0.wav	2.369 s, 252 MB
earnings-calls/60_5_31.wav	2.15 s, 261 MB
earnings-calls/94_13_97.wav	2.124 s, 262 MB
librispeech-other/5484-24317-0027.wav	2.066 s, 262 MB
librispeech-clean/5683-32866-0019.wav	2.008 s, 262 MB

Recipe: board/targets.py. Run: 2026-11-06T19:41:17Z, Python 3.13.18, Linux x86_64, 4 CPUs (log). Installed: RapidFuzz==3.14.6, certifi==2026.10.23, cffi==2.1.1, charset-normalizer==3.5.2, idna==3.20, indic_numtowords==1.1.0, more-itertools==11.2.1, pycparser==3.12, regex==2026.9.29, requests==2.34.2, srt==3.5.3, text2num==3.1.0, tqdm==4.70.1, urllib3==2.8.0, vosk==0.3.45, websockets==17.4, whisper_normalizer==1.0.0