Other
SpeechRecognition: Library for performing speech recognition, with support for several engines and APIs, online and offline
Anthony Zhang (Uberi), GitHub, project README, n.d.
Read the originalRead on October 17, 2026
- What it is
- The README of the open-source SpeechRecognition Python package. It lists the engines and web APIs the package can call, which ones work offline, and the requirements for microphone input.
- How much weight it carries
- Written by the package's maintainer and kept with the code, so it describes the current behavior. It does not give accuracy figures; the engines it wraps are separate products with their own terms.
Facts taken from this source
- The SpeechRecognition package lists Vosk and OpenAI's Whisper among the engines it can call, both marked as working offline, alongside the Google Speech Recognition endpoint.
“Vosk API (works offline) OpenAI whisper (works offline)” (Engine and API support list)
- The SpeechRecognition package needs the separate PyAudio package only if you want to use microphone input; the rest of the library works without it.
“PyAudio is required if and only if you want to use microphone input” (Requirements: PyAudio)