remotion-voicevox-template  by nyanko3141592

AI-driven animated dialogue video generation template

Created 2 months ago
252 stars

Top 99.6% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a template for creating dialogue-driven videos featuring characters like Zundamon and Metan, leveraging AI for script generation and voice synthesis. It targets content creators and users who want to produce animated explainer videos, tutorials, or social media content efficiently, offering a streamlined workflow that combines conversational AI with automated video rendering.

How It Works

The template integrates Remotion for video rendering, VOICEVOX for high-quality text-to-speech, and Claude Code for interactive script creation. Users converse with Claude Code to define video content, which then generates dialogue. VOICEVOX synthesizes speech from this dialogue, and Remotion animates characters with lip-sync and facial expressions, rendering the final video. Configuration for fonts, colors, and layout is managed via YAML files, allowing for easy customization.

Quick Start & Requirements

  • Primary Install/Run:
    1. Clone the repository: git clone https://github.com/nyanko3141592/remotion-voicevox-template.git my-video
    2. Navigate to the directory: cd my-video
    3. Install dependencies: npm install
    4. Start VOICEVOX application.
    5. Run preview server: npm start (access at http://localhost:3000)
    6. Start Claude Code for video creation: claude (in a separate terminal)
  • Prerequisites: Node.js 18+, VOICEVOX (running application), Claude Code (recommended).
  • Links:

Highlighted Details

  • Interactive AI Scripting: Utilizes Claude Code to generate video scripts and dialogue through natural language conversation.
  • Automated Voice & Animation: Employs VOICEVOX for realistic speech synthesis and automatically generates lip-sync animations for characters.
  • Expression & Customization: Supports multiple character expressions (happy, surprised, thinking, sad) and allows easy visual customization of fonts, colors, and layout via video-settings.yaml.
  • Audio Enhancements: Includes support for adding background music (BGM) and sound effects (SE) to enrich video production.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), or project roadmap are provided in the README.

Licensing & Compatibility

The template code is released under the MIT License. However, users must comply with the individual terms of service for the VOICEVOX software and the character assets (Zundamon, Metan), which are available on their respective official websites. Compatibility for commercial use is subject to these external terms.

Limitations & Caveats

The project requires external applications (VOICEVOX, Claude Code) to be installed and running. Character image assets for lip-sync and expressions are optional; placeholders are used if custom images are not provided. Advanced customization or troubleshooting may necessitate familiarity with Remotion and TypeScript.

Health Check
Last Commit

2 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
15 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.