{"data":{"slug":"alphacep-vosk-api","name":"vosk-api","tagline":"Offline speech recognition API","github_url":"https://github.com/alphacep/vosk-api","owner":"alphacep","repo":"vosk-api","owner_avatar_url":"https://avatars.githubusercontent.com/u/26358566?v=4","primary_language":"Jupyter Notebook","stars":15137,"forks":1759,"topics":["android","asr","deep-learning","deep-neural-networks","deepspeech","google-speech-to-text","ios","kaldi","offline","privacy","python","raspberry-pi","speaker-identification","speaker-verification","speech-recognition","speech-to-text","speech-to-text-android","stt","voice-recognition","vosk"],"archived":false,"github_pushed_at":"2026-08-09T13:35:47+00:00","maintenance_label":"Steady","stars_delta_30d":124,"url":"https://www.graphcanon.com/tools/alphacep-vosk-api","markdown_url":"https://www.graphcanon.com/tools/alphacep-vosk-api.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alphacep-vosk-api","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alphacep-vosk-api","description":"Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node","homepage_url":null,"license":"Apache-2.0","open_issues":605,"watchers":142,"ai_summary":"Vosk is an offline open source toolkit for speech recognition supporting over 20 languages and dialects with small models, continuous large vocabulary transcription, and speaker identification.","readme_excerpt":"# Vosk Speech Recognition Toolkit\n\nVosk is an offline open source speech recognition toolkit. It enables\nspeech recognition for 20+ languages and dialects - English, Indian\nEnglish, German, French, Spanish, Portuguese, Chinese, Russian, Turkish,\nVietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino,\nUkrainian, Kazakh, Swedish, Japanese, Esperanto, Hindi, Czech, Polish.\nMore to come.\n\nVosk models are small (50 Mb) but provide continuous large vocabulary\ntranscription, zero-latency response with streaming API, reconfigurable\nvocabulary and speaker identification.\n\nSpeech recognition bindings implemented for various programming languages\nlike Python, Java, Node.JS, C#, C++, Rust, Go and others.\n\nVosk supplies speech recognition for chatbots, smart home appliances,\nvirtual assistants. It can also create subtitles for movies,\ntranscription for lectures and interviews.\n\nVosk scales from small devices like Raspberry Pi or Android smartphone to\nbig clusters.\n\n# Documentation\n\nFor installation instructions, examples and documentation visit [Vosk\nWebsite](https://alphacephei.com/vosk).","github_created_at":"2019-09-03T17:48:42+00:00","created_at":"2026-07-11T12:14:20.843462+00:00","updated_at":"2026-09-20T07:15:42.985539+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"android","name":"android"},{"slug":"asr","name":"asr"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"deeplearning","name":"deeplearning"},{"slug":"deepspeech","name":"deepspeech"},{"slug":"google-speech-to-text","name":"google-speech-to-text"},{"slug":"ios","name":"ios"},{"slug":"kaldi","name":"kaldi"}],"trust":{"provenance":{"is_fork":false,"github_id":206138137,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T07:15:41.161Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":0,"days_since_push":41,"last_release_at":"2024-04-22T13:02:41Z","stars_delta_30d":124,"open_issues_delta_30d":5},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:14:22.687Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T07:15:42.434Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-09-20T07:15:42.434Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T07:15:42.434Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When offline operation is required as Vosk operates without internet connection","For applications needing to run on limited hardware like Raspberry Pi or mobile platforms due to its low resource footprint","In scenarios where privacy is a concern and data should not be sent over the network for processing"],"when_not_to_use":["When the project requires real-time transcription with high accuracy, possibly surpassing Vosk's performance limitations","For projects limited to languages not currently supported by Vosk's model lineup","If the application necessitates a cloud solution or benefits from regular over-the-air updates and improvements"],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:05:24.419Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Vosk-api is an offline speech recognition toolkit enabling continuous large-vocabulary transcription for over 20 languages, fitting onto small devices while offering speaker identification."}]}}