Glossary

Voxta-specific

Voxta — AI orchestration platform for natural voice and text chat with AI characters.

Voxta Server — the local desktop app that runs orchestration, services, and the web UI.

Voxta Cloud — Voxta's hosted AI backend. Provides LLM, TTS, and STT through a single API.

Voxy — desktop avatar companion that connects to Voxta Server and adds a VRM-rendered face.

Studio — the authoring half of Voxta — characters, scenarios, interactions, scripts.

Character — an AI persona (name, description, personality, voice, profile, assets).

Scenario — the situation a character operates under: roles, interactions, scripts, app configuration.

Role — a named slot in a scenario that a character is assigned to. Templates and scripts address characters by role, not by name.

Interaction — the umbrella for the things a scenario can fire: events, buttons, HUD widgets, actions, tools and contexts.

Action — something the AI does alongside speaking, chosen by a dedicated inference pass. See actions and tools.

Action Inference — that dedicated pass, which picks at most one action per layer.

Tool — the other half of the same object: something the character calls itself while writing a reply, and sees the result of.

Event — a story beat that fires on its own, on a trigger anchored to the chat start, a flag, or another event.

Button — a clickable interaction shown to the player during a chat.

Context — sentences added to the prompt just before the AI's reply (e.g. {{ char }} is wearing a blindfold).

Memory Book — a set of entries recalled when the conversation matches them. Either lore you authored, or the character's own private book. See memory books.

Understanding — a character's standing model of the people it talks to, rewritten as it develops and always in the prompt. Distinct from memories, which are events that happened.

Flag — a boolean state bit used to gate interactions. Flags sharing a prefix. are mutually exclusive.

Variable — a named value a script or control writes, persisted with the chat. Readable in conditions as $name and in templates as {{ variables.name }}.

Chat Style — Companion, Roleplay, Storytelling or Assistant. Decides which interactions are offered.

App Trigger — a call from a scenario script to the host app (Voxta Talk, Voxta-VAM, Voxy) to change UI state, play audio, swap avatars, and so on.

Stage — the visual-novel chat view: a background, buttons placed on it, and the HUD.

Package — a bundle of resources and their assets, shared as a .voxpak. See packages.

Augmentation — a service that adds context or capabilities to a chat: vision, documents, web search, MCP tools, a game integration.

AI / ML jargon

AI (Artificial Intelligence) — broad term for systems that simulate intelligent behavior.

LLM (Large Language Model) — a model trained on huge text corpora that can read and generate language. Powers the character's replies.

TTS (Text-to-Speech) — turns text into spoken audio. Voxta's voice services.

STT (Speech-to-Text) — turns spoken audio into text. Voxta's transcription services.

Token — the basic unit an LLM reads and writes. Roughly a word or part of a word. "Unbelievable" might be three tokens: un + believ + able.

Context window — the maximum number of tokens an LLM can consider at once. Older messages get dropped or summarized when the chat exceeds it.

Summarization — compressing old chat history into a shorter summary so the context window doesn't fill up.

Quantization — compressing a model's weights to reduce its memory footprint. Trade some accuracy for fitting on consumer GPUs.

GGUF / EXL2 / GPTQ / AWQ — quantization formats for local LLMs. See LLM overview.

RAG (Retrieval-Augmented Generation) — feeding an LLM with retrieved-on-demand information instead of stuffing everything into the prompt up front.

RLHF (Reinforcement Learning from Human Feedback) — fine-tuning an LLM using human ratings to align its outputs.

MoE (Mixture of Experts) — an LLM architecture that activates only a subset of its parameters per query.

AGI (Artificial General Intelligence) — hypothetical AI capable of any intellectual task a human can. Aspirational target, not currently shipped.

Adjacent tech

VR (Virtual Reality) — immersive simulated environment via a headset.

VAM (Virt-A-Mate) — 3D character creation and interaction software, designed for VR. Voxta integrates via a plugin.

Mocap (Motion Capture) — recording human movement for animation playback. SMPL is a popular mocap representation.

SMPL / SMPL-H — a 3D body model representing a pose as joint rotations plus a root translation. Used by HyMotion and other text-to-motion models.

VRM (VRoid Model) — a standard 3D humanoid avatar file format. Used by Voxy and many VTubing apps.

Tools and platforms

HF (Hugging Face) — central hub for open-source ML models.

API (Application Programming Interface) — a set of endpoints / functions exposed for other programs to call. An API key authenticates which program is calling.

SDK (Software Development Kit) — a bundle of libraries and tools for building on a platform.

MCP (Model Context Protocol) — open standard for exposing tools and resources to LLMs. Voxta supports MCP via the HTTP and STDIO augmentations.