Very often I need to verify whether a video containing certain keywords that I am looking for. That is very difficult to be done unless I watch the entire video or download the subtitle. However, most videos do not have a subtitle inside.
I then found out the transcription services on the Internet but the price is quite expensive. Fortunately, Google Cloud Platform offers API to its speech-to-text AI-enhanced model. The price is also so much reasonable.
Here are the steps I did:
1) Download FLAC audio extract from youtube videos;
2) Upload the audio files to Google cloud storage (long audio files could only be transcribed if stored in GCS);
3) Run the transcription program (follow the official guide: https://lnkd.in/eJcHfJ6)