Skip to content

Latest commit

 

History

History

Demo1

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
speaking-clock
speaking-clock
 
 
README.md
README.md
 
 
SSML.txt
SSML.txt
 
 
Studio.url
Studio.url
 
 
speaking-clock.png
speaking-clock.png
 
 
studio.png
studio.png
 
 
text-to-speech.url
text-to-speech.url
 
 

README.md

M04 DEMO #1

  • Text to Speech
  • SSML

This code is provided for demo purposes only for course AI-102.

Requirements

  • Azure Subscription
  • Node.js (optional)
  • VS Code (optional)

Text to Speech

  1. Follow the link to demonstrate text to speech capabilities by providing sample text and select voice to synthesize a speech.

  2. Switch to SSML tab and provide content of SSML.txt file

Speech Studio

  1. Build new if it does not exist cognitive multi-service in Azure portal.

  2. Open speech portal https://speech.microsoft.com/portal and sign in with your azure subscription account.

  3. Demonstrate several voices from Voice Gallery. Some of the voices support emotion.

  4. Switch to the Audio content creation. You can add a different voices from Voice Gallery and use SSML markup to manage pronunciation.

studio

Speaking clock (optional)

  1. For successful run you need to install SoX and related NPM package.

  2. The code based on the hands-on example converted to Node.js and adopted to execute on RPi. The sample is working with a microphone and expects input like 'What time is it?'

  3. Original code and installation instruction can be found in following repo

speaking-clock

The sample includes Speech recognition and Speech synthesizing code examples.