Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
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.
Stars
8,959
Forks
2,434
Language
Python
License
BSD-3-Clause
Category
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.
Featured in
Related tools
cmusphinx/pocketsphinx
A small speech recognizer
istupakov/onnx-asr
A lightweight Python package for Automatic Speech Recognition using ONNX models
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition