stephengrice / synth-me

Basic concatenative text-to-speech implementation in Python
17 stars 3 forks source link

synth-me

Synth-me is a concatenative text-to-speech engine implemented in Python.

I started this project in January 2015 because I was intrigued by text-to-speech software and wanted to learn more about how it worked.

A concatenative text-to-speech engine creates an audio representation of text by pasting together a bunch of small audio files to form the whole of the output.

There are three steps, including:

Dependencies

This project relies on Python 3.x.

Installation

Follow the steps below to try the speech synthesizer out.

  1. Make sure that all dependencies are installed.
  2. Clone or download this repository to your local machine.
  3. Open a terminal and navigate to the cloned directory.
  4. Run: pip install -r requirements.txt
  5. Run the command python3 synthme.py
  6. You will be prompted for a message. Enter what you want the engine to say!
  7. The program will end. Open output.wav to hear the result.