All Software > Video Production > Vtuber Assistant
Community Hub
Vtuber Assistant
Your customizable AI co-host & beginner VTuber rig. Live face tracking, animations, and reactions — no setup hassle. Local fallback + premium AI voices. Fun from second one.

Sign in to add this item to your wishlist, follow it, or mark it as ignored

Features
In-App Purchases
Profile Features Limited 
Requires agreement to a 3rd-party EULA
Languages:
Interface Full Audio Subtitles
English ✔ ✔
Content
Includes Interactive Elements

In-game purchases, Online interactivity

Early Access Software

Get involved with this software as it develops.

Note: This Early Access software is not complete and may or may not change further. If you are not excited to use this software in its current state, then you should wait to see if it progresses further in development. Learn more

What the developers have to say:

Why Early Access?

“Vtuber Assistant is a passion project born from wanting a real AI companion that could both act as a desktop pet and double as a beginner-friendly VTuber rig. Early Access lets me involve the community early—your feedback on AI reactivity, tracking polish, pluggable integrations, animation layering, and overall usability will directly shape updates. This is the best way to build something that truly fits what streamers, VTubers, and casual users actually want.”

Approximately how long will this software be in Early Access?

“We plan for Early Access to last 6–12 months, depending on community feedback and feature pace. The goal is to reach a stable 1.0 with core polish, expanded reactivity, and robust pluggable support, but the timeline will flex based on what matters most to users.”

How is the full version planned to differ from the Early Access version?

“We plan to expand scope in these areas during Early Access and beyond:

-Deeper AI brain integration (more contextual synthesis, better multi-input understanding).
-Expanded reaction library (pre-made & user-contributed animations, expressions, VFX).
-More pluggable options (additional model support, advanced TTS/STT integrations).
-UI/UX polish (hotkey customization, preset saves, better onboarding for beginners).
-Performance & stability improvements across Windows, Linux, macOS, and Steam Deck.
-We won't make hard promises on exact timelines or features—development will evolve with your input.”

What is the current state of the Early Access version?

“The Early Access version is fully playable and feature-complete for core use cases:

-Drag-and-drop desktop overlay with resize/positioning (OBS-friendly).
-Toggle between user-controlled facial tracking (webcam, overlay mask, extra bones, sliders/toggles) and AI co-host mode.
-Live reactivity to system audio, visual screen capture, Twitch chat, and voice/text input.
Generative AI responses (local default + user-pluggable online), TTS voice output, layered animations under tracking.
-Custom personality prompts, safety guard, and modular pluggable system.
It's stable for daily use (streaming, gaming, casual hanging out), but will continue to receive polish, bug fixes, and new features based on feedback.”

Will this software be priced differently during and after Early Access?

“I want to be clear, I do not plan to increase the price after early access. If anything I have thoughts to lower it depending on how wide spread this goes. To be honest I am playing this by ear.”

How are you planning on involving the Community in your development process?

“Community input is central:

-Steam reviews, discussions, and feedback threads will guide priorities (e.g., which integrations or reactions matter most).
-In-app feedback forms and Discord (if created) for direct suggestions.
Regular devlogs/news updates on Steam showing what's being worked on and why.
-Beta branches for testing new features before wider release.
-Roadmap visibility: I'll share planned additions and adjust based on what users vote for or request most.”
Read more
This game is not yet available on Steam

Planned Release Date: To be announced

Interested?
Add to your wishlist and get notified when it becomes available.
 
See all discussions

Report bugs and leave feedback for this software on the discussion boards

EARLY ACCESS LAUNCH!!! – Shape the Future!

Vtuber Assistant is heading to Early Access — and we want YOU in from day one!

This is your chance to get the app early, play with the core rig + local AI co-host, and directly influence what comes next. Your feedback, roasts, clips, and ideas will shape updates.

Roadmap Highlights (what we're prioritizing based on community input):

• Smarter AI brain — better aggregation from visual/audio/user input for more contextual reactions

• Expanded animation layering & hotkey options

• Bigger reaction & personality library

• More pluggable support (voices, models, behaviors)

• Workshop-style profile sharing

• Community soundboard & custom packs

The base app is already beginner-friendly and fully playable offline — Early Access means more polish, more features, and YOUR voice in development.

How to help right now:

• Wishlist on Steam → helps visibility & shows demand

• Drop a review (even short) once live → guides what we build next

Let's build something wild together. See you in Early Access!

— Draven

About This Software

Vtuber Assistant – Your Customizable AI Co-Host & Avatar

Bring your own personality to life — as a full VTuber avatar for streaming or a reactive desktop companion that chats, reacts, and vibes with you. Built for beginners: no rigging nightmares, no complex setup, just instant fun.

Core Features (All Included – No Keys Required)

• Import any .VRM model — easy drag-and-drop with built-in bone correction to fix scuffed poses for smooth resting stance.

• Face tracking with any webcam — live mirroring in seconds.

• Animation hotkeys — trigger reactions (happy, sad, dance, taunt, etc.) on demand.

• Upload your own animations (.VRMA) and VRM models — make it truly yours.

• Basic AI co-host — local fallback models (SmolLM2 chat + Piper TTS) for offline text responses and voice. Reacts to your voice, text input, and screen content.

• Desktop pet mode — overlay on your desktop, idle animations, and simple reactivity.

• Stream-ready tools — experimental OBS wizard for quick integration and hotkeys for live control.

Free tier gives you the full rig + tracking + basic local AI — no API keys or external setup required.

AI Boost (experimental): Unlock smarter responses (Grok) and premium voices (ElevenLabs Turbo v2.5) via optional Steam microtransactions (AI Credits packs).

Due to Steam policy, advanced AI features are handled through microtransactions.

Future Ideas (Early Access Roadmap)

• Workshop profiles — share and download custom personalities, voices, and setups.

• AI-controlled soundboard — let your companion trigger reactions automatically.

• More upload options — custom animations, models, and sound packs.

Perfect for casual VTubers, streamers needing a sassy sidekick, video creators wanting an AI commentator, or anyone who wants a customizable desktop buddy that talks back.

Not a brainless pet. Fully yours. Way more fun.

AI Generated Content Disclosure

The developers describe how their game uses AI Generated Content like this:

Vtuber Assistant uses generative AI to create live text responses and voice output as a customizable co-host companion. It reacts to your voice/text input, screen audio/visuals, and Twitch chat with fun, contextual commentary.

All core functionality runs through a secure built-in proxy by default (Grok + ElevenLabs integration) — no external API keys or setup required to use the app. Free limited daily uses are included.

Optional premium features (unlimited generations, premium voices) are handled via Steam microtransactions (AI Credits packs). Local fallback models (bundled SmolLM2 + Piper TTS) provide offline functionality when needed.

Twitch chat integration is read-only — the AI consumes incoming messages and produces in-app responses only.

All outputs are moderated by a built-in Safety Guard to help prevent inappropriate content.

System Requirements

Windows
SteamOS + Linux
    Minimum:
    • OS: Windows 10 (64-bit) or later
    • Processor: Intel Core i5 6th Gen / AMD Ryzen 3 or equivalent
    • Memory: 8 GB RAM
    • Graphics: Integrated GPU with WebGL 2.0 support (Intel UHD 630 / AMD Radeon RX 550 or better)
    • Storage: 2 GB available space
    • Sound Card: Any
    • Additional Notes: Webcam (720p+) required for face tracking; Microphone for voice input. Works fully offline with bundled AI.
    Recommended:
    • OS: Windows 11 (64-bit)
    • Processor: Intel Core i7 9th Gen+ / AMD Ryzen 5 5600X+ or better
    • Memory: 16 GB RAM
    • Graphics: Dedicated GPU (NVIDIA GTX 1660 / AMD RX 5600 XT or equivalent)
    • DirectX: Version 12
    • Network: Broadband Internet connection
    • Storage: 6 GB available space
    • Sound Card: Any
    • Additional Notes: Dedicated GPU accelerates vision AI models. 1080p webcam recommended.
    Minimum:
    • OS: Ubuntu 20.04+ / Fedora 38+ / SteamOS 3+ or equivalent modern distro
    • Processor: Intel Core i5 6th Gen / AMD Ryzen 3 or equivalent
    • Memory: 8 GB RAM
    • Graphics: GPU with WebGL 2.0 support (Intel/AMD integrated or NVIDIA/AMD dedicated)
    • Storage: 2 GB available space
    • Sound Card: Any
    • Additional Notes: Webcam (720p+) and microphone required. Tested on Bazzite/Steam Deck. Flatpak or AppImage recommended for immutable distros.
    Recommended:
    • OS: Latest Ubuntu / Fedora / SteamOS
    • Processor: Intel Core i7 9th Gen+ / AMD Ryzen 5 5600X+
    • Memory: 16 GB RAM
    • Graphics: Dedicated GPU (NVIDIA/AMD with ROCm/CUDA support preferred)
    • Network: Broadband Internet connection
    • Storage: 6 GB available space
    • Sound Card: Any
    • Additional Notes: GPU acceleration for AI models; Steam Deck compatible in desktop mode.
There are no reviews for this product

You can write your own review for this product to share your experience with the community. Use the area above the purchase buttons on this page to write your review.