Uberi/speech_recognition

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

What it solves

This library provides a unified interface for performing speech recognition in Python, allowing developers to easily switch between different speech-to-text engines and APIs without rewriting their core logic. It simplifies the process of capturing audio from a microphone or file and converting it into text, supporting both online cloud services and offline local engines.

How it works

The library acts as a wrapper around multiple speech recognition backends. It provides a consistent set of tools to handle audio input (via PyAudio for microphones) and then routes that audio to a chosen recognition engine. Supported backends include:

  • Offline engines: CMU Sphinx, Vosk, and OpenAI Whisper.
  • Online APIs: Google Speech Recognition, Google Cloud Speech, Wit.ai, Microsoft Azure Speech, Houndify, IBM Speech to Text, OpenAI Transcription API, Groq Whisper API, and Cohere Transcribe API.

It also includes utility functions to calibrate for ambient noise and manage audio data encoding (e.g., using FLAC).

Who it’s for

Developers building voice-controlled applications, transcription tools, or any software that requires converting spoken audio into text using a variety of available AI models and services.

Highlights

  • Multi-engine support: Compatible with a wide array of local and cloud-based speech-to-text providers.
  • Online and Offline: Supports fully offline recognition for privacy or low-latency needs via Sphinx, Vosk, or Whisper.
  • Flexible Input: Can process audio directly from the microphone or from existing audio files.
  • Ambient Noise Handling: Includes features to calibrate the energy threshold to better handle background noise.

Related

  • Project
    absadiki/pywhispercpp

    Python bindings for whisper.cpp that provide a simple API for high-performance speech-to-text transcription with support for multiple hardware acceleration backends.

  • Project
    VOICEVOX/voicevox_core

    The core speech synthesis engine for VOICEVOX, provided as a C and Python library for easy integration into various applications.

  • Project
    ahmetoner/whisper-asr-webservice

    A general-purpose speech recognition toolkit that wraps Whisper models into a REST API for easy deployment and integration.

  • Project
    codeforequity-at/botium-speech-processing

    A unified API for open-source and cloud-based Speech-To-Text and Text-To-Speech services, simplifying audio processing for chatbots and voice applications.

  • Project
    nateshmbhat/pyttsx3

    A Python library for offline text-to-speech conversion that utilizes native system engines to generate voice output without an internet connection.