alphacep/vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

81
/ 100
Verified

Built on lightweight acoustic models (50MB), Vosk delivers continuous large-vocabulary transcription with zero-latency streaming and reconfigurable vocabulary across 20+ languages. The toolkit supports speaker identification and exposes a streaming API with bindings across Python, Java, Node.js, C++, Rust, and Go, scaling from embedded devices to server clusters. Primary use cases include chatbot integration, smart home voice control, virtual assistants, and media subtitle generation.

14,377 stars and 320,271 monthly downloads. Used by 6 other packages. Available on PyPI.

Maintenance 10 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

14,377

Forks

1,687

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Feb 22, 2026

Monthly downloads

320,271

Commits (30d)

0

Dependencies

5

Reverse dependents

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/alphacep/vosk-api"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.