Design. Direct. Render.
Most AI tools are just generators. This is a Director's Studio.
The first Non-Linear Editor (NLE) with a Dynamic Plugin System for local AI audio.
Requires NVIDIA GPU & Windows 10/11
Don't just generate lines; build scenes. The block-based editor allows you to mix multiple speakers, clone voices, and custom designs into a single script.
Features a "Traffic Light" system to track generation status and a smart stitching engine to render full conversations instantly.
The first extensible AI audio suite. Drop new features into the modules/ folder to add custom tabs, automation scripts, and entirely new workflows without touching the core code.
Comes with a Developer SDK and automated scripting support via callbacks.
Turn any audio file into a digital actor. The integrated cloning engine uses "Lock Voice" technology to cache speaker profiles, allowing for instant generation without re-processing.
Includes a Multi-Part Mode to handle long scripts by splitting them automatically.
Good data equals good audio. The Prep Station includes a built-in Whisper AI engine to auto-transcribe your reference files.
Record from your microphone or system audio, crop the waveform visually, and send it directly to the cloner.
"I am a Creative Engineer driven by a lifelong fascination with what technology can do. My journey began in the 80s, writing code in MS-BASIC with a manual as thick as a phone book."
I explore these tools not to build walls, but to break them down. We evolve by sharing and integrating. This software is my contribution to that evolution—making pro-grade AI audio tools accessible to everyone.