Uberi /speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
★ 9,004⑂ 2,417👁 263⑃ 269● 639▤ 45
+0
Daily
9,004
stars
2,417
forks
263
watchers
269
prs
639
issues
45
releases
Top issues
#326AttributeError: Could not find PyAudio; check installation Raspberry Pi 334 comments · 2018-02-15#385Speech_recognition broken for new Bing API16 comments · 2018-11-09#575speech_recognition.RequestError: recognition request failed: Bad Request12 comments · 2021-07-22#334Google Cloud Speech : "Invalid JSON payload received. Unknown name "speech_context" at 'config': Cannot find field."12 comments · 2018-03-11#798myRecognizer object freezes the script when using `.listen` method (sometimes)11 comments · 2024-12-04#526"ALSA lib unable to open slave" When calling Microphone()10 comments · 2020-10-19#556raise AttributeError("Could not find PyAudio; check installation") AttributeError: Could not find PyAudio; check installation9 comments · 2021-03-13#508pyaudio after installation not working9 comments · 2020-08-31
Latest release
3.17.0 3.17.0 2026-06-17SpeechRecognition 3.17.0 is out🎉
This release adds AudioData.split() for large audio file.
Get all of these updates with a quick pip install --upgrade SpeechRecognition.
Enjoy!
Features
feat: Add AudioData.split() for chunking large audio data by @ftnext in https://github.com/Uberi/speech_recognition/pull/896
Example: https://github.com/Uberi/speech_recognition/pull/896issuecomment-4720478780
chore: Remove retired recognize_bing (Microsoft Bing Speech API) by @ftnext in https://github.com/Uberi/speech_recognition/pull/901
Improvements
chore: Install ffmpeg direct in Linu