https://github.com/veeeetzzzz/mars5-tts

Python implementation for the MARS5 TTS repo that allows you to clone a voice with a command line interface.
https://github.com/veeeetzzzz/mars5-tts

Last synced: about 2 months ago
JSON representation

Python implementation for the MARS5 TTS repo that allows you to clone a voice with a command line interface.

• Host: GitHub
• URL: https://github.com/veeeetzzzz/mars5-tts
• Owner: Veeeetzzzz
• License: agpl-3.0
• Created: 2024-06-29T18:24:07.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-11T17:55:41.000Z (6 months ago)
• Last Synced: 2024-07-11T19:24:14.181Z (6 months ago)
• Language: Python
• Homepage:
• Size: 811 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MARS5 Text-To-Speech (TTS) Deep Voice Clone

[![CodeFactor](https://www.codefactor.io/repository/github/veeeetzzzz/mars5-tts/badge)](https://www.codefactor.io/repository/github/veeeetzzzz/mars5-tts)

This is a Python implementation for the [MARS5 TTS repo](https://github.com/Camb-ai/MARS5-TTS) that allows you to clone a voice with a command line interface.

Try the [online demo here](https://6b1a3a8e53ae.ngrok.app/) for a quickstart or follow the instructions below to run this project locally/offline

# Roadmap

- EZ front end

- Enable PyTorch CUDA (supported devices only)

# Installation

Install [Python](https://www.python.org/downloads/)

Clone directory/download [.zip file](https://github.com/Veeeetzzzz/mars5-tts/archive/refs/heads/main.zip)

Open CMD/Powershell in directory and run      

                              

    pip install -r requirements.txt

# Usage

## Visual Studio Code

Download/clone this repo and open the folder in Visual Studio Code

![image](https://github.com/Veeeetzzzz/mars5-tts/assets/40268197/09059ae7-cdfe-4c47-a6a3-07143849377f)

Find your Terminal and run 

    python tts.py # where tts.py is the file name of the Python script

![image](https://github.com/Veeeetzzzz/mars5-tts/assets/40268197/6f525c5c-0c98-4642-961c-82c4d3712e5a)

You'll be taken through the steps to start cloning - fill in your own values or press ENTER for default.

![image](https://github.com/Veeeetzzzz/mars5-tts/assets/40268197/0b4bed6b-2aa0-459e-b765-a45320919cce)

## Command Line/PowerShell

Download/clone this repo and open Command Line/PowerShell from the folder (File -> Open PowerShell Window)

![image](https://github.com/Veeeetzzzz/mars5-tts/assets/40268197/2e1e6077-1d0f-4009-898d-fad2a7b3d386)

There's no impact on us whether we use Command Line or PowerShell. They look the same in terms of input/output.

    python tts.py

![image](https://github.com/Veeeetzzzz/mars5-tts/assets/40268197/ba1fae6e-b614-4ff6-95da-e176717652f4)

# Notes

- Keep reference voice between 6-10 seconds

- Tune config to get optimal output

- Provide transcript when possible

- Use sample provided for ease

# Known issues

- System won't lock up but CPU usage remains at 100% throughout processing stage

- Results will vary - this is not a one shot model but seems far more impressive than ElevenLabs, Speechify at the cost of processing time