I need a service that can take audio files and transcribe them into text. I’m very keen on translating to Mandarin (Traditional) as well as Spanish.
AWS Transcribe will do the trick….but I’ll have to test how much this project is going to cost me.
The first half of the project is finished. A user can access my frontend application (contact me for the password) in S3 from this website (sequence 1 thru 10 in the image below).
- User browses to the webpage that has a link to my AWS S3 landing page.
- User clicks the link and is directed
- The S3 reponds with html land page
- User injects a video file (.mp4) onto the landing page and click “Upload Video”. An API request is directed to the AWS API Gateway.
- The API Gateway directs the request to a lambda backend
- Lambda function interfaces with the S3 bucket to generate a one-time URL code
- The URL code is past back to Lamda
- Lambda function returns the URL code to the gateway
- Gateway sends the response data back to the computer
- Finally, the computer can use the one-time URL to send a PUT request to the S3 bucket. The S3 bucket approves the request and the .mp4 file is uploaded to S3.