HAKORADev/VODER

What it solves

VODER is a comprehensive, all-in-one local toolkit for professional-grade audio and media processing. It eliminates the need for multiple subscription-based services by consolidating complex tasks like voice cloning, speech-to-text, music generation, and video dubbing into a single, offline-capable interface.

How it works

The project acts as an orchestrator for various state-of-the-art open-source AI models. It provides a unified command-line interface (and GUI) to run these models locally. Users can execute individual tasks or create "chains"—user-defined pipelines that wire multiple operations together (e.g., generating music, isolating vocals, and then dubbing a video) in a single command. It also includes "Project Eva," a modular expansion that adds visual and 3D generation capabilities using the same infrastructure.

Who it’s for

It is designed for creators, developers, and power users who need to perform high-quality audio and video manipulation locally without relying on cloud services. It is particularly useful for those who want to automate complex media workflows through scripting or command-line pipelines.

Highlights

• Comprehensive Audio Suite: Supports 8 core modes including speech-to-text, text-to-speech, voice conversion, music generation, and speaker diarization.
• Pipeline Automation: The "Chains" feature allows users to link multiple AI tasks into automated, end-to-end workflows.
• Project Eva DLC: Extends functionality to include text-to-image, text-to-video, 3D world generation, and uncensored text-to-text chat.
• Smart Input: Automatically processes various media sources, including direct URLs from major social platforms and image-based text extraction.
• Local & Private: Runs entirely on the user's machine with no subscription requirements, working with or without a GPU.