Install ‐ Text‐generation‐webui Installation

This guide provides quick setup instructions for installing AllTalk TTS version 2 as an extension for Text-generation-webui (TGWUI) on Windows and Linux platforms.

Note for Existing AllTalk V1 Users - If you have an existing AllTalk installation, you'll need to rename your old alltalk_tts folder or install this version in a different location. A fresh install is currently required due to necessary Python environment rebuilding.

READ THIS BEFORE INSTALLING INTO TGWUI

OCTOBER 13th 2024 There are current issues around requirements files, explained here. Please read that first before installing AllTalk. You are currently best installing AllTalk as a Standalone install and using the TGWUI Remote Extension option until I can update the integration in future. Click the explained here link for more detail.

Remote Extension Option

Aside from installing AllTalk directly within Text-generation-webui, AllTalk can be integrated as a remote extension if you prefer (otherwise follow the instructions further down this page). The Remote Extension Option allows you to use AllTalk's TTS capabilities without installing it directly within Text-generation-webui's Python environment. It's ideal for users who want to run AllTalk on separate hardware or in its own Standalone Python environment.

Features/Benefits:

• Connect to a remote AllTalk server from Text-generation-webui
• Access all AllTalk TTS features through Text-generation-webui interface
• Maintain separate Python environments or hardware for Text-generation-webui and AllTalk
• Avoid Python environment conflicts if TGWUI's requirements are updated sooner than AllTalk's

For more information on setting up AllTalk as a remote extension, please refer to the Remote Extension Guide.

Prerequisites

Windows Prerequisites

Before installing AllTalk, ensure you have the following:

• Git for cloning GitHub repositories. Installation instructions
• Microsoft C++ Build Tools and Windows SDK for proper Python functionality. Installation instructions
• Espeak-ng for multiple TTS engines to function. Installation instructions

If you already have these installed, you can proceed directly to the Quick Setup instructions.

Linux Prerequisites

Depending on your Linux distribution, you'll need to install some packages for AllTalk and its TTS engines to function correctly:

• Debian-based systems (e.g., Ubuntu):

  sudo apt install libaio-dev espeak-ng ffmpeg gcc g++
  

• RPM-based systems (e.g., CentOS, Fedora):

  sudo yum install libaio-devel espeak-ng ffmpeg gcc g++
  

Important:

• Avoid using dashes or spaces in your folder path (e.g., avoid my folder-is-this/alltalk_tts-main) as this causes issues with Python.
• Make sure you have a working installation of Text-generation-webui.

Quick Setup - Text-generation-webui installations

For a video guide on the TGWUI installation process, visit: TGWUI Installation Guide

Windows Instructions

1. Open Command Prompt and navigate to the TGWUI extensions directory:

   cd /d C:\path\to\text-generation-webui\extensions
   

2. Clone the AllTalk repository:

   git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
   

3. Start the TGWUI Python environment:

   cd ..
   cmd_windows.bat
   

4. Navigate to the AllTalk directory:

   cd extensions\alltalk_tts
   

5. Run the setup script:

   atsetup.bat
   

6. Follow the on-screen instructions to install necessary requirements.
   
   

Linux Instructions

1. Open a terminal and navigate to the TGWUI extensions directory:

   cd /path/to/text-generation-webui/extensions
   

2. Clone the AllTalk repository:

   git clone -b alltalkbeta https://github.com/erew123/alltalk_tts
   

3. Start the TGWUI Python environment:

   cd ..
   ./cmd_linux.sh
   

4. Navigate to the AllTalk directory:

   cd extensions/alltalk_tts
   

5. Run the setup script:

   ./atsetup.sh
   

6. Follow the on-screen instructions to install necessary requirements.
   
   

Additional Notes

• It's recommended to test AllTalk's functionality before installing DeepSpeed.
• Always activate the appropriate Python environment before making adjustments or using features like Fine-tuning.
• For more detailed instructions on Fine-tuning and DeepSpeed, refer to the setup utility and the full documentation.
• If you're new to Python environments, consider reviewing the Understanding Python Environments Simplified section in the Help documentation.