Generates google speech api response from any video using google cloud functions and google cloud storage
This project when run will generate a speech api json file from the provided videos.
The Project is not updated in a very long time. I am being really busy, but I am trying to revive this. Feel free to provide suggestions and improvements. I am available on Twitter @Abhi347.
gcloud config list
command. If no configuration is found, run gcloud init
.app-config.json
.npm install
.video
, audio
and speechResponse
bucket names in app-config.json
file with the name of your own GCS bucket names.npm run deploy
command.app-config.json
.audio
bucket as a flac file of the same name as the video file.speechResponse
bucket.extractAudio
will watch for any new upload in the video
bucket.extractAudio
function will extract the audio from the file and upload the audio as a flac file with the same name as the video file to the audio
bucket.transcribeAudio
will watch any new upload in the audio
bucket.extractAudio
function uploads the extracted flac audio file to the audio
bucket, the transcribeAudio
function will be triggered.transcribeAudio
function will then upload the audio file to the google speech api.speechResponse
bucket.video
bucket or any other file than an flac audio file to audio
bucket.transcribeAudio
cloud function by editing it.The original idea and most of the source is taken from the Hackernoon article mentioned below. I have created this repo, because they didn't provided any working code, just code fragments. The code is modularised and the deploy script is created by me.