Vosk
Vosk is an offline open source speech recognition toolkit. It enables speech recognition for 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino...
Cost / License
- Free
- Open Source
EUPlatforms
- Windows
- Linux
- Mac
Vosk
Features
Properties
- Privacy focused
Features
- Speech Recognition
- Speech to text
- Voice recognition
- Multiple languages
- Offline
Tags
- deep-learning
- vosk
- kaldi
- speaker-verification
- Raspberry Pi
- ios
- deepspeech
- Android
- stt
- google-speech-to-text
- deep-neural-networks
- asr
- Python
- speech-to-text-android
- speaker-identification
Vosk News & Activities
Recent activities
- 3rd reviewed Vosk
5 stars? Well, it's one of a kind :D And it does a pretty good job but that heavily depends on the circumstances (chosen model, speaker, language, background noise etc).
And it's a good start for automated subtitling:
vosk-transcriber -n vosk-model-en-us-0.42-gigaspeech -i input.mkv -t srt -o output.srt
NB: It's not perfect, YMMV!
PS: You can have also a lot of fun if chose the wrong language ;)
PSPS: If you look for alternatives, have a look...
Vosk information
Developed by
alphacep Licensing
Open Source (Apache-2.0) and Free product.Alternatives
0 alternatives listedSupported Languages
- English
AlternativeTo Category
DevelopmentGitHub repository
- 13,928 Stars
- 1,641 Forks
- 578 Open Issues
- Updated
What is Vosk?
Vosk is an offline open source speech recognition toolkit. It enables speech recognition for 20+ languages and dialects - English, Indian English, German, French, Spanish, Portuguese, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish. More to come.
Vosk models are small (50 Mb) but provide continuous large vocabulary transcription, zero-latency response with streaming API, reconfigurable vocabulary and speaker identification.
Speech recognition bindings implemented for various programming languages like Python, Java, Node.JS, C#, C++, Rust, Go and others.
Vosk supplies speech recognition for chatbots, smart home appliances, virtual assistants. It can also create subtitles for movies, transcription for lectures and interviews.
Vosk scales from small devices like Raspberry Pi or Android smartphone to big clusters.
Comments and Reviews
5 stars? Well, it's one of a kind :D And it does a pretty good job but that heavily depends on the circumstances (chosen model, speaker, language, background noise etc).
And it's a good start for automated subtitling:
vosk-transcriber -n vosk-model-en-us-0.42-gigaspeech -i input.mkv -t srt -o output.srt
NB: It's not perfect, YMMV!
PS: You can have also a lot of fun if chose the wrong language ;)
PSPS: If you look for alternatives, have a look here https://fosspost.org/open-source-speech-recognition