Check this for youtube 2 text that detect requires online

[codenamewei]

Each Recognizer instance has seven methods for recognizing speech from an audio source using various APIs. These are:

recognize_bing(): [Microsoft Bing Speech](https://azure.microsoft.com/en-us/services/cognitive-services/speech/)
recognize_google(): [Google Web Speech API](https://w3c.github.io/speech-api/speechapi.html)
recognize_google_cloud(): [Google Cloud Speech](https://cloud.google.com/speech/) - requires installation of the google-cloud-speech package
recognize_houndify(): [Houndify](https://www.houndify.com/) by SoundHound
recognize_ibm(): [IBM Speech to Text](https://www.ibm.com/watson/services/speech-to-text/)
recognize_sphinx(): [CMU Sphinx](https://cmusphinx.github.io/) - requires installing PocketSphinx
recognize_wit(): [Wit.ai](https://wit.ai/)

Of the seven, only recognize_sphinx() works offline with the CMU Sphinx engine. The other six all require an internet connection.

https://realpython.com/python-speech-recognition/