vosk
Offline open source speech recognition API based on Kaldi and Vosk
Decision gist · record as of 2026-08-14
Yes, if you need offline speech recognition and can tolerate medium install friction and model file management. The permissive license, active maintenance, and lack of known vulnerabilities make it a solid choice for privacy-focused or bandwidth-constrained deployments. Not recommended if you require state-of-the-art accuracy or support for languages beyond the 20+ listed.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Vosk model file (approximately 50 Mb per language) to be downloaded separately and available on disk; audio input source must be configured.
- Medium install friction due to platform-specific wheels and compiled dependencies via cffi.
- Active maintenance with recent commits and strong community engagement (15056 GitHub stars), though the latest release was 2022-12-14.
License · maintenance · safety
permissive license (permissive) — Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions—suitable for most production and proprietary projects.
last release 2022-12-14 (1339 days) · last repo commit 2026-08-09 · 15,056 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 677,961 downloads/mo, #5,379 on PyPI
Alternatives
Verify before relying
pip install vosk
import vosk
from vosk import Model, KaldiRecognizer
model = Model(lang="en-us")
recognizer = KaldiRecognizer(model, samplerate)- Whether models for all 20+ languages are actively maintained and available for download
- Performance characteristics (latency, accuracy) compared to cloud-based alternatives
- Exact sample rate and audio format requirements for the streaming API
What it is and what it does
Vosk is a Python binding for an offline speech recognition engine based on Kaldi. It transcribes audio to text without sending data to external servers, making it suitable for privacy-sensitive applications, embedded systems, and environments without reliable internet. The package wraps compiled Kaldi models and provides a streaming API that processes audio chunks in real time, returning partial and final transcriptions as they become available.
The toolkit supports 20+ languages and dialects with relatively small model files (around 50 Mb each). It's designed to scale from resource-constrained devices like Raspberry Pi to larger deployments, and includes features like reconfigurable vocabulary and speaker identification. Common use cases include chatbot backends, smart home voice control, video subtitle generation, and lecture transcription.
Use it for
- Build a voice-controlled chatbot or virtual assistant that processes audio locally without cloud dependency
- Generate subtitles for video or audio recordings by transcribing speech to text offline
- Add voice commands to a Raspberry Pi or embedded Linux device for IoT applications
- Transcribe interviews or lectures with privacy guarantees and no per-minute API costs
- Implement speaker identification or custom vocabulary matching in voice-driven workflows
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need offline speech recognition and can tolerate medium install friction and model file management.
The permissive license, active maintenance, and lack of known vulnerabilities make it a solid choice for privacy-focused or bandwidth-constrained deployments. Not recommended if you require state-of-the-art accuracy or support for languages beyond the 20+ listed.
Install
vosk on PyPI
Before you install
Medium install friction due to platform-specific wheels and compiled dependencies via cffi. Active maintenance with recent commits and strong community engagement (15056 GitHub stars), though the latest release was 2022-12-14.
Requires a Vosk model file (approximately 50 Mb per language) to be downloaded separately and available on disk; audio input source must be configured.
License in practice
Licensed under Apache Software License (permissive), allowing commercial and private use with minimal restrictions—suitable for most production and proprietary projects.
Quickstart
pip install vosk
import vosk
from vosk import Model, KaldiRecognizer
model = Model(lang="en-us")
recognizer = KaldiRecognizer(model, samplerate)Verify before relying
- Whether models for all 20+ languages are actively maintained and available for download
- Performance characteristics (latency, accuracy) compared to cloud-based alternatives
- Exact sample rate and audio format requirements for the streaming API
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 5 packagescffirequeststqdmsrtwebsockets |
| Maintenance | Actively maintained 1,339 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 677,961 / month, #5,379 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: MacOS :: MacOS XOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Topic :: Software Development :: Libraries :: Python Modules |
Evidence: vosk-0.3.45-py3-none-linux_armv7l.whl; vosk-0.3.45-py3-none-manylinux2014_aarch64.whl; vosk-0.3.45-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl; vosk-0.3.45-py3-none-win_amd64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “offline speech recognition”
- voskVosk provides offline speech recognition for 20+ languages, enabling…
- SpeechRecognitionPerforms speech recognition and transcription using multiple online…
- pocketsphinxPocketSphinx provides Python bindings for Carnegie Mellon…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also SpeechRecognition · openai-whisper · qwen-asr · sherpa-onnx · deepgram-sdk · livekit-plugins-soniox · qwen-tts · pocketsphinx · sherpa-onnx-core · vokativ