SpeechRecognition

What SpeechRecognition is

SpeechRecognition is a free Python library that connects speech-recognition projects to a range of engines and APIs, with online and offline options. Supported services include CMU Sphinx, Google Speech Recognition, Google Cloud Speech API, Wit.ai, Microsoft Azure Speech, Houndify, IBM Speech to Text, Vosk, Whisper, Groq Whisper, and Cohere Transcribe. CMU Sphinx, Snowboy Hotword Detection, Vosk, and Whisper are identified as working offline. Examples cover microphone input, audio-file transcription, saving audio, extended results, ambient-noise calibration, and background microphone listening. The easiest installation method listed is `pip install SpeechRecognition`; installation from the PyPI source distribution is also described. Python 3.10 or later is required. PyAudio 0.2.11 or later is needed only for microphone input; other library features work without it. Google Cloud Speech use requires local Google credentials, while OpenAI and Groq recognizers require environment API keys. The OpenAI transcription recognizer supports compatible self-hosted endpoints such as vLLM and Ollama. The library is under the 3-clause BSD license; included FLAC binaries use GPLv2.

Who it suits

It suits Python developers building speech recognition with a choice of online, offline, or self-hosted options. Users should account for the Python requirement and any credentials or optional microphone dependency needed for their chosen recognizer.

Limits

Python 3.10 or later is required. PyAudio 0.2.11 or later is required for microphone input, and Google Cloud Speech API V2 is unsupported.

Getting started

1. Open the SpeechRecognition project website.
2. Install Python 3.10 or later.
3. Install the library with `pip install SpeechRecognition`, or use the PyPI source distribution.
4. Install PyAudio 0.2.11 or later if you will use microphone input.
5. Add local Google credentials for Google Cloud Speech, or environment API keys for OpenAI or Groq, when using those recognizers.

Verdict

SpeechRecognition offers a broad interface for speech recognition in Python, including offline and self-hosted choices. Requirements vary by feature and engine, so check the relevant dependency and credentials before choosing an option.