
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
15,000
±0 (Oct 13〜)
Last commit
Oct 2026
Created on GitHub
Sep 3, 2019
Listed
—
Listed since the page was created
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | — |
| May 2026 | — |
| Jun 2026 | — |
| Jul 2026 | — |
| Aug 2026 | — |
| Sep 2026 | 15,000 |
| Oct 2026 | 15,000 |
| Nov 2026 | 15,000 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Use on PyPI
PyPI packages: vosk · Monthly figures to Oct 2026 (ClickPy)
Downloads, last 12 months
6,092,061
Share from Japan (last 12 months)
1.0%
PyPI packages that depend on it
123
94 as a required dependency
Monthly downloads on PyPI
Show as a table
| Month | downloads (month) |
|---|---|
| Jan 2019 | — |
| Feb 2019 | — |
| Mar 2019 | — |
| Apr 2019 | — |
| May 2019 | — |
| Jun 2019 | — |
| Jul 2019 | — |
| Aug 2019 | — |
| Sep 2019 | — |
| Oct 2019 | — |
| Nov 2019 | — |
| Dec 2019 | 540 |
| Jan 2020 | 1,870 |
| Feb 2020 | 3,513 |
| Mar 2020 | 1,624 |
| Apr 2020 | 5,459 |
| May 2020 | 7,373 |
| Jun 2020 | 10,157 |
| Jul 2020 | 5,371 |
| Aug 2020 | 6,034 |
| Sep 2020 | 7,938 |
| Oct 2020 | 10,373 |
| Nov 2020 | 7,281 |
| Dec 2020 | 12,101 |
| Jan 2021 | 9,942 |
| Feb 2021 | 9,033 |
| Mar 2021 | 10,856 |
| Apr 2021 | 9,046 |
| May 2021 | 12,044 |
| Jun 2021 | 11,391 |
| Jul 2021 | 10,697 |
| Aug 2021 | 8,589 |
| Sep 2021 | 10,642 |
| Oct 2021 | 12,161 |
| Nov 2021 | 10,809 |
| Dec 2021 | 11,179 |
| Jan 2022 | 13,593 |
| Feb 2022 | 14,567 |
| Mar 2022 | 18,841 |
| Apr 2022 | 17,439 |
| May 2022 | 20,551 |
| Jun 2022 | 20,445 |
| Jul 2022 | 18,340 |
| Aug 2022 | 18,132 |
| Sep 2022 | 19,996 |
| Oct 2022 | 23,479 |
| Nov 2022 | 24,111 |
| Dec 2022 | 22,010 |
| Jan 2023 | 18,373 |
| Feb 2023 | 21,290 |
| Mar 2023 | 27,223 |
| Apr 2023 | 29,457 |
| May 2023 | 27,681 |
| Jun 2023 | 22,766 |
| Jul 2023 | 24,332 |
| Aug 2023 | 27,159 |
| Sep 2023 | 31,254 |
| Oct 2023 | 32,483 |
| Nov 2023 | 30,599 |
| Dec 2023 | 34,250 |
| Jan 2024 | 36,809 |
| Feb 2024 | 38,141 |
| Mar 2024 | 46,243 |
| Apr 2024 | 56,523 |
| May 2024 | 54,011 |
| Jun 2024 | 57,596 |
| Jul 2024 | 66,422 |
| Aug 2024 | 65,110 |
| Sep 2024 | 69,198 |
| Oct 2024 | 91,571 |
| Nov 2024 | 90,058 |
| Dec 2024 | 83,146 |
| Jan 2025 | 87,009 |
| Feb 2025 | 105,467 |
| Mar 2025 | 121,549 |
| Apr 2025 | 119,986 |
| May 2025 | 130,849 |
| Jun 2025 | 131,698 |
| Jul 2025 | 134,277 |
| Aug 2025 | 153,753 |
| Sep 2025 | 176,512 |
| Oct 2025 | 193,432 |
| Nov 2025 | 216,359 |
| Dec 2025 | 194,789 |
| Jan 2026 | 191,269 |
| Feb 2026 | 222,356 |
| Mar 2026 | 338,735 |
| Apr 2026 | 429,570 |
| May 2026 | 623,880 |
| Jun 2026 | 674,216 |
| Jul 2026 | 677,961 |
| Aug 2026 | 769,107 |
| Sep 2026 | 606,604 |
| Oct 2026 | 1,147,215 |
Popular in the same category
whisperopenai110kRobust Speech Recognition via Large-Scale Weak Supervision.
whisper.cppggml-org54kPort of OpenAI's Whisper model in C/C++.
faster-whisperSYSTRAN26kFaster Whisper transcription with CTranslate2.
whisperXm-bain24kWhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
FunASRmodelscope21kOpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
NeMo SpeechNVIDIA-NeMo19kA scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Resources in similar research fields
- wav2vec2-large-xlsr-53-japanesejonatasgrosman16MJapanese wav2vec‑2 XLSR‑53 fine‑tuned on Common Voice 6.1, CSS10, and JSUT, requiring 16 kHz audio and usable via HuggingSound or HuggingFace pipelines.HF modelShared: Speech recognition
kaldikaldi-asr15kkaldi-asr/kaldi is the official location of the Kaldi project.Shared: Speech recognition- wav2vec2-large-xlsr-japanese-hiraganavumichien153kA Japanese speech‑recognition model fine‑tuned from facebook/wav2vec2‑large‑xlsr‑53 on Common Voice and the JSUT corpus, optimized for 16 kHz audio input.HF modelShared: Speech recognition
espnetespnet10kEnd-to-End Speech Processing Toolkit.Shared: Speech recognition
SenseVoiceQwenAudio9.4kOpen-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.Shared: Speech recognition
argmax-oss-swiftargmaxinc6.4kOn-device Speech AI for Apple Silicon.Shared: Speech recognition