1. Upload Voxta JSON File

Upload the character.json from your Voxta companion profile.

Technical Documentation: Mapping Specialized Companions to Foundation Schemas

The migration from **Voxta** to **Pygmalion** is a technical process of down-sampling a hardware-aware, high-immersion "Companion Entity" into a format optimized for the foundational JSON standards of the AI roleplay community. While Voxta is built for multimodal presence, Pygmalion serves as the classic prefix-based bridge for numerous roleplay frontends and early inference tools.

1. Schema Simplification and Key Re-Mapping

Voxta uses a rigid, capitalized JSON structure designed to drive specialized inference weights. Fields like Personality and Profile are critical for Voxta's behavioral engine. Pygmalion utilizes a foundational flat-schema with explicit prefixes like char_name and char_persona. Our converter identifies these specialized Voxta keys and intelligently merges them into the standard Pygmalion fields, ensuring the character's internal logic remains cohesive during the simplification process.

2. Deconstructing Hardware-Ready Metadata

Voxta characters are anchored by a UUID and often contain metadata optimized for Text-to-Speech (TTS) and movement engines. Pygmalion JSON is focused purely on text-based narrative interaction. Our converter strips out these hardware-specific triggers and re-focuses the character data on linguistic traits and scenario context, ensuring that the resulting JSON is lightweight and fully compatible with legacy roleplay tools that lack Voxta's advanced companion features.

3. Dialogue and Example Normalization

Voxta dialogue examples (MesExample) are often formatted for vocal clarity and may include voice-engine artifacts. Pygmalion-compatible models perform best with clean, narrative-driven dialogue. Our engine scans the Voxta source, removes TTS cues, and reformats the dialogue into the classic Pygmalion pattern. This ensures that the character's unique cadence and speaking style are preserved while ensuring maximum readability for the inference model.

4. Privacy and Data Sovereignty

We believe that your companions are deeply personal creative works. By using a "Zero-Server" architecture, we perform the entire schema translation within your browser's RAM. Your companion's backstory, personality settings, and unique voice cues are never transmitted to our server or any third party. This provides a secure, private bridge for creators who want to maintain absolute control over their digital assets as they move them between platforms.

5. Ensuring Cross-Frontend Compatibility

By outputting a standardized Pygmalion JSON, we ensure that your Voxta companions can be used across a vast array of legacy tools and specialized roleplay frontends. This conversion process isn't just about moving a file; it's about future-proofing your digital characters and ensuring they remain accessible, editable, and compatible with the broader AI ecosystem, regardless of how specialized their original source format may be.