No panel, no tablet, no macros to memorize
Use the camera you already have to turn a smile, glance, blink, or thumbs-up into live-stream actions.
A hands-free Stream Deck alternative: detects face and hands locally to activate scenes, overlays and alerts in OBS, Streamlabs, vMix, PRISM and XSplit. No memorized hotkeys, no extra hardware, no video sent to the cloud.
No trial · 3 devices · Twitch/YouTube/Trovo + Kick via Streamer.bot · Updates included
OBS, Streamlabs, vMix, PRISM, XSplit + Twitch, YouTube, Trovo, Kick via Streamer.bot
What streamers search for
EsperantAI matches the daily setup intent: control OBS without hotkeys, switch scenes when your hands are busy, and automate overlays without buying more hardware.
Use the camera you already have to turn a smile, glance, blink, or thumbs-up into live-stream actions.
OBS, Streamlabs, vMix, PRISM and XSplit respond to configurable gestures for scenes, sources, sounds and overlays.
When your hands are on a controller, guitar, knife or stylus, your face can trigger the exact live moment.
Detection runs in your browser with WebGL. Video stays on your device while gestures are recognized.
Platform search intent
If your community uses channel points, follows, raids, Super Chat or tips, EsperantAI turns those events into visual actions and can confirm them with a gesture.
Trigger a scene, overlay or sound when the event arrives, then use a smile, thumbs-up or glance as human confirmation.
Turn support moments into scene changes, alerts or overlays without taking your hands off the stream.
Use Streamer.bot as the bridge for Kick events and let EsperantAI add the gesture layer.
Twitch, YouTube, Trovo and StreamElements can share the same map of gestures, scenes and overlays.
How it works
No heavy installation, no learning curve. Your first session is ready in under 5 minutes.
EsperantAI detects your camera automatically. Works with any USB 1080p webcam or your laptop's built-in cam.
~ 30 secondsGuided wizard: smile, nod, give a thumbs-up. EsperantAI learns your ranges in 90 seconds.
~ 90 secondsConnect OBS, Streamlabs, vMix, PRISM, or XSplit; optionally add Twitch/YouTube/Trovo + Kick via Streamer.bot. Each gesture can switch a scene, overlay, alert, or sound.
∞ hours without a keyboardBody control · Invisible automation
Switch scenes, fire a sound, activate an overlay, or respond to a sub without breaking the conversation with your audience.
Turn toward a side camera and the scene follows your movement. The audience perceives human intent, not a hidden keypress.
Works with OBS via WebSocket, Streamlabs Desktop, vMix HTTP, PRISM with obs-websocket plugin, and XSplit through a local bridge.
A thumbs-up can trigger an overlay, sound, or thank-you scene when a sub, raid, or donation arrives.
In Pro+, a sub, raid, or donation can wait for your physical confirmation before launching a full sequence.
Auto-detects your system locale. One-click manual switch.
AI runs locally with WebGL and browser acceleration. Zero video uploaded. Zero external telemetry.
Human interaction
When you turn left and the scene changes, or raise a thumb and an overlay appears, the activation feels like part of the dialogue with the viewer: a natural reaction, not a technical interruption.
You look toward the side camera and the live show follows that movement with a prepared scene.
A thumbs-up can become an overlay, sound, or thank-you scene right when an event arrives.
The technology stays behind. What the audience perceives is presence, intent, and human timing.
Universal by design
Facial expressions are pre-linguistic: a smile means the same thing in Tokyo, Lagos, or Bogotá. EsperantAI maps that universal language to actions, while the interface adapts to 15 languages.
"Facial expressions are universal across all human cultures."
— Paul Ekman, Universals and Cultural Differences in Facial Expressions of Emotion, 1972
Verified compatibility
No lock-in, no extra hardware. Your current setup stays your setup.
Why "EsperantAI"
Eksponentigu viajn fluojn per gestoj.
— in Esperanto: "Multiply your streams with gestures."Esperanto was a human attempt to create a universal language in 1887. It failed as a spoken language, but the ideal lives on. Gestures, however, truly are universal: pre-linguistic, biological, millions of years of shared evolution.
EsperantAI is the artificial intelligence that finally speaks the only language all humans share. That's why every gesture is tagged as Universal (smile, nod, gaze) or Cultural (thumbs-up, OK, peace) — you decide which ones to use based on your global audience.
Extended demo
OBS setup, gesture calibration, combo triggers in action, and multi-action per gesture.
PRO streaming · MXN pricing
No free version, no trial. Buy through secure Lemon Squeezy checkout and receive your license key by email.
For individual streamers who want scenes, overlays and alerts triggered by gestures in their current setup.
One-time payment · 3 devices · non-expiring license
For creators who monetize and want event + gesture: subs, raids, donations and alerts with human confirmation.
One-time payment · 3 devices · non-expiring license
Final digital product · No trial · No refund after license issue or activation (policy) · Purchase subject to EULA and anti reverse-engineering restrictions
Frequently asked questions
Pro includes everything an individual streamer needs: 5 software, 4 platforms (Twitch/YouTube/Trovo + Kick via Streamer.bot), 18 triggers, personalized calibration, hand gestures, all universal gestures.
Pro+ adds 3 extra features: combo triggers (platform event + physical human confirmation gesture), StreamElements bridge (a single integration for Twitch + YouTube + Facebook), and unlimited triggers.
No. EsperantAI is sold only through its Pro and Pro+ plans. The reason: the product requires license activation to work against the validation backend, and activation is irreversible (see No-refund policy).
If you want to see EsperantAI in action before buying, check out the demo videos on this same page and the user manual with real screenshots of the app.