Uberi/speech_recognition

Speech recognition module for Python, supporting several engines and APIs, online and offline.

90
/ 100
Verified

Provides a unified interface abstraction over 12+ speech recognition backends (Google, Azure, IBM, OpenAI Whisper, Vosk, CMU Sphinx, etc.), enabling developers to swap engines without rewriting code. Handles audio acquisition from microphone or file input, applies preprocessing like noise calibration and energy thresholding, and supports both cloud APIs and local offline models. Includes hotword detection (Snowboy) and optional language pack customization for multilingual support across backends.

8,959 stars. Used by 18 other packages. Actively maintained with 62 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

8,959

Forks

2,434

Language

Python

License

BSD-3-Clause

Last pushed

Mar 11, 2026

Commits (30d)

62

Dependencies

3

Reverse dependents

18

Get this data via API

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

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