Dubbing Studio

An AI-powered dubbing platform designed to transform a single voice actor or actress into an entire cast of characters through voice conversion, emotional speech synthesis, and localization workflows.

CORE TECHNOLOGIES

Unity Core application framework used to integrate AI voice technologies, audio processing and localization workflows.

RVC Open-source Voice Changer

ElevenLabs Premium Voice Changer + Text To Speech

FFmpeg Audio Processing + Fast Video merger

Localization Used For Localization Dubbing

FEATURED PROJECT

Download Now

FramePack Plus Extended

Extended AI video generation and multi-keyframe workflows.

CORE TECHNOLOGIES

FramePack AI video generation framework for long-form video creation.

HunyuanVideo AI video generation model powering the workflow.

Python Core programming language used for the system.

Gradio Web interface used for interactive generation.

FEATURED PROJECT

FramePack Plus Extension

FramePack Plus is an open-source project built around AI video generation workflows, originally supporting Start and End Keyframes for controlling the beginning and ending states of a generated sequence.

My contribution focuses on extending this workflow with multi-keyframe support, allowing multiple keyframes to be arranged into a sequence and used to guide different stages of the generated animation.

This project is featured in my portfolio as an example of extending an existing open-source AI workflow, integrating new functionality, and building a more flexible interface around the generation pipeline.

Git Repository

← Back to Areas of Expertise