0

I am thinking to create an application.

Following are the description: 1. People will upload previously recorded conversation to the server. 2. application from the server will detect pitch, speed,emphasis,pronunciation etc of that voice and create a personal portfolio. 3. If you call to the server then server application will talk with you in the exact voice tone of that person(whose voice server detected in Step 2).

Please share links, resources, pdf presentation whatever you find useful for this project.....

Mainly I am stuck on the STEP 2. I don't have clear idea how to break down a voice and analysis it and get info of Speed, Pitch etc. Is there any existing API available for the voice part?

Md Romel
  • 1
  • 1

1 Answers1

0

I was able to find this :

You might also check into this SO question:

Community
  • 1
  • 1
rlb.usa
  • 14,942
  • 16
  • 80
  • 128