A Python library that performs speech recognition across multiple online and offline engines. It accepts microphone and audio file inputs and returns text transcriptions.
Project overview
A Python library that performs speech recognition across multiple online and offline engines. It accepts microphone and audio file inputs and returns text transcriptions.
Project type
Audio & Speech
Use cases
Translation & Subtitles
Deployment
Refer to project documentation
License
BSD-3-Clause
Best for
Developers needing a Python library that performs speech recognition using multiple online and offline engines.
Developers who require microphone input, audio file transcription, or background listening within their Python applications.
Key capabilities
Performs speech recognition using multiple engines and APIs, supporting both online and offline modes.
Captures speech input directly from a microphone.
Transcribes spoken audio from an audio file.
Calibrates the recognizer energy threshold for ambient noise levels.
Listens to a microphone in the background.
Limitations and risks
PyAudio 0.2.11 or later is required only if you need to use microphone input or the Microphone functionality.
External services are optional, and paid services may be optional depending on the chosen engine or API integration.
Getting started
Install the library easily via pip using the command 'pip install SpeechRecognition'.
Evidence and sources
README: Library for performing speech recognition, with support for several engines and APIs, online and offline.
GitHub project description: Speech recognition module for Python, supporting several engines and APIs, online and offline.
README: Recognize speech input from the microphone
README: Transcribe an audio file
README: Calibrate the recognizer energy threshold for ambient noise levels