🎭 Guided setup

Your AI Companion
for Live Streams

Meet a character, share your game, and bring your co-host into OBS. Start with a private sample reaction.

1

Meet your co-host

Pick a personality in Studio, optionally add your nickname, and try a free sample reaction. Nothing is sent to OBS and no screen is shared. Listen with browser speech to try the idea; this does not preview a premium provider's voice.

🔷
Byte
Tactical & witty
👾
Fizz
Maximum hype
🍡
Mochi
Cozy & chill
🛡️
Pixel
Retro RPG hero
👻
Error
Nervous intern
🎀
Celest
Sweet helper
You can also write a custom prompt to create your own personality from scratch.
2

Share your game

Open Share game in Avatar Studio, check your capture-history preference, and choose a game window in the browser sharing picker. Starting sharing enables reactions using your saved settings. Keep the tab open while sharing.

The desktop app is optional: it can capture without keeping the Studio tab open. Browser sharing sends game screenshots for analysis or to your connected agent; microphone audio is not included. Stop sharing with the browser controls or the Studio Stop button.
3

Add to OBS

Copy your Avatar URL into a Browser Source at 400 × 300. Send a text test, check that it appears in OBS, then click I can see it in OBS. Copying a URL alone does not confirm a working source.

Check your audio in OBS separately. Browser speech adds no voice-credit charge. Premium voices, quality and your own API keys are available under Settings & customization.
4

Run your session

Session shows whether reactions are enabled, recent screen input, output activity and your latest capture or agent reaction. A preview tab can count as output activity; this does not prove a live broadcast.

That was a sick play!
🎀

Browser Source Setup

Copy the overlay URL from Avatar Studio, add it as a Browser Source in OBS, and position it on your scene.

400 × 300 px
Pause co-host stops reactions and browser sharing in this tab. If the desktop app is capturing, stop it separately. The sidebar shows your saved per-look and voice costs. Scene changes can add reactions between scheduled looks.

Ready to set up your avatar?

Meet → Share game → Add to OBS → Session. Choose Just Chatting for a browser conversation, or My own AI agent for MCP setup.

Frequently Asked Questions

Do I need to pay for anything?
The private sample reaction is free and sees no screen. Real AI analysis and generated voice can spend credits; your balance and saved costs appear in the Studio sidebar. Your own API keys or AI agent are billed by their provider. Voice input, memory and other features retain their subscription requirements.
Are my API keys safe?
Yes. Your keys are stored securely and are never returned by the API after saving. You'll only see a masked version (e.g., sk-...xY). You can remove a key at any time by entering __clear__ in the key field.
How does screen capture work?
Use browser game-window sharing in Studio or the optional desktop app. Frames are sent for AI analysis or held temporarily for your connected agent. Check Settings → Privacy to control capture-history storage before sharing.
Can I create my own personality?
Absolutely. Pick any companion as a base, then write a custom prompt in the Studio to override or extend their personality. You can make your avatar say anything in any style.
What is the Memory feature?
When enabled, your avatar remembers its recent comments and uses them as context for new responses. This makes conversations feel more natural — it won't repeat itself and can reference things it said earlier. You can set the memory depth from 1 to 50 messages.
Does the overlay work with Streamlabs?
Yes — any streaming software that supports Browser Sources (OBS, Streamlabs, XSplit, etc.) will work. Just paste the overlay URL and set the dimensions to 400×300.