Voice Generator Documentation

Introduction: Voice Generator is a powerful addon for Blender that allows you to synthesize speech from text using the MeloTTS API. Whether you're working on animation projects, video editing, or multimedia presentations, this addon provides a convenient way to add natural-sounding voiceovers to your creations.

Installation:

1. Download the Voice Generator addon from the provided source.
2. Open Blender and navigate to Edit > Preferences > Add-ons.
3. Click on "Install" and select the downloaded addon file.
4. Enable the addon by checking the checkbox next to its name.
5. Click "Save Preferences" to confirm.

Getting Started:

1. Once installed, you can find the Voice Generator addon in the Video Editing tab of Blender.
2. Click on the Voice Generator panel to access its features.

Features:

1. Speaker Selection:

• Choose from various pre-defined speakers including English (US), English (UK), English (India), English (Australia), Spanish, French, Chinese, Japanese, and Korean.

2. Text Input:

• Enter the text you want to synthesize into speech in the provided text input field.

3. Speed Adjustment:

• Adjust the speed of speech synthesis using the speed slider. Increase for faster speech or decrease for slower speech.

4. Language Selection:

• Select the language for the synthesized speech from the available options.

5. Synthesize Speech:

• Click the "Generate Voice" button to initiate the speech synthesis process.

Usage:

1. Select the desired speaker, enter the text, adjust the speed and language settings as needed.
2. Click the "Generate Voice" button to synthesize speech from the provided text.
3. Once synthesized, the audio file will be added to the Blender sequencer automatically.

Tips and Tricks:

• Experiment with different speakers and languages to find the most suitable voice for your project.
• Fine-tune the speed settings to match the pacing of your animation or video.

Compatibility:

• Voice Generator addon is compatible with Blender version 3.6, 4.0 and above.

Troubleshooting:

• If you encounter any issues or errors, please refer to the addon documentation or contact support for assistance.

Voice Generator 2.0 Documentation

Introduction

Voice Generator 2.0 is a powerful Blender addon designed to synthesize speech from text using the Hugging Face Space API. This addon seamlessly integrates with Blender's interface, allowing users to generate high-quality audio for their video editing projects. With Voice Generator 2.0, you can bring characters to life, narrate scenes, and enhance storytelling with synthesized speech.

Installation

1. Download the Voice Generator 2.0 addon file.
2. Launch Blender.
3. Go to Edit > Preferences.
4. Click on the Add-ons tab.
5. Click on the Install button.
6. Navigate to the location where you saved the addon file, select it, and click Install Add-on.
7. Once installed, enable the addon by checking the box next to "Voice Generator 2.0" in the Add-ons list.
8. Click on the Save Preferences button to apply the changes.

Using Voice Generator 2.0

Step 1: Accessing the Addon

1. Open Blender.
2. Navigate to the View3D workspace.
3. Locate the Sidebar panel on the right side of the screen.
4. Scroll down to find the Voice Generator 2.0 section.

Step 2: Input Text

1. Enter the text you want to synthesize in the "Input Text" field.
2. This is the text that will be converted into speech.

Step 3: Selecting Speaker Voice

1. Choose the desired speaker voice from the dropdown menu under "Speaker Voice."
2. Voice Generator 2.0 supports various speaker options, including different accents and languages.

Step 4: Adding Emotion Prompts (Optional)

1. If desired, select an emotion prompt from the dropdown menu under "Emotion Prompts."
2. Emotion prompts add nuance to the synthesized speech, such as laughter, sighs, or music cues.

Step 5: Generating Voice

1. Once you've configured the settings, click on the "Generate Voice" button to synthesize the speech.
2. Voice Generator 2.0 will communicate with the Hugging Face Space API and generate the audio based on your input text and selected parameters.
3. The synthesized audio will be added to the Blender Sequencer as an audio strip, starting from frame 1.

Tips and Tricks

• Experiment with different speaker voices and emotion prompts to achieve the desired tone and expression in your synthesized speech.
• Use non-speech sounds like laughter, sighs, or music cues to add realism and depth to your audio tracks.