Text-To-Speech Module

[chidiewenike]

Objective

Explore offline Text-To-Speech (TTS) libraries that will convert a string to audio.

Key Result

Create a function that will output raw audio bytes from a string input.

Details

The function will take, as input, a string which will be the output from Rasa. The string is then converted to raw audio bytes by an offline/local TTS library. When selecting the appropriate library, priorities are as follows:

1. Memory
2. Runtime
3. Speaker Quality
4. Customizability of sound properties

[mfekadu]

useful comment in issue #2

#2 (comment)

[nguyenlienviet]

The pyttsx3 library is offline and doesn't seem to use much memory. However, it doesn't have a method to return audio bytes and only has a method to play the audio instead; would this work for our use case @chidiewenike ?. I'm not sure if it will work out of the box on the pi, but it's very easy to use so you can just try on your pi.

[gwholland3]

It can also save the audio to a file, in mp3 format I believe. Would that help?

[chidiewenike]

Playing the audio within the function using the pyttsx3 module is fine.