VisionClaw

A real-time AI assistant for Meta Ray-Ban smart glasses. See what you see, hear what you say, and take actions on your behalf -- all through voice.

Built on Meta Wearables DAT SDK (iOS) / DAT Android SDK (Android) + Gemini Live API.

Supported platforms: iOS (iPhone) and Android (Pixel, Samsung, etc.)

What It Does

Put on your glasses, tap the AI button, and talk:

• "What am I looking at?" -- Gemini sees through your glasses camera and describes the scene

The glasses camera streams at ~1fps to Gemini for visual context, while audio flows bidirectionally in real-time.

How It Works

Meta Ray-Ban Glasses (or phone camera)
       |
       | video frames + mic audio
       v
iOS / Android App (this project)
       |
       | JPEG frames (~1fps) + PCM audio (16kHz)
       v
Gemini Live API (WebSocket)
       |
       |-- Audio response (PCM 24kHz) --> App --> Speaker
       |
       v
  Gemini speaks the result

Key pieces:

• Gemini Live -- real-time voice + vision AI over WebSocket (native audio, not STT-first)
• Phone mode -- test the full pipeline using your phone camera instead of glasses
• WebRTC streaming -- share your glasses POV live to a browser viewer

---

Quick Start (iOS)

1. Clone and open

git clone https://github.com/sseanliu/VisionClaw.git
cd VisionClaw/samples/CameraAccess
open CameraAccess.xcodeproj

2. Add your secrets

Copy the example file and fill in your values:

cp CameraAccess/Secrets.swift.example CameraAccess/Secrets.swift

Edit Secrets.swift with your Gemini API key (required) and optional WebRTC config.

3. Build and run

Select your iPhone as the target device and hit Run (Cmd+R).

4. Try it out

Without glasses (iPhone mode):

1. Tap "Start on iPhone" -- uses your iPhone's back camera
2. Tap the AI button to start a Gemini Live session
3. Talk to the AI -- it can see through your iPhone camera

With Meta Ray-Ban glasses:

First, enable Developer Mode in the Meta AI app:

1. Open the Meta AI app on your iPhone
2. Go to Settings (gear icon, bottom left)
3. Tap App Info
4. Tap the App version number 5 times -- this unlocks Developer Mode
5. Go back to Settings -- you'll now see a Developer Mode toggle. Turn it on.

Then in VisionClaw:

1. Tap "Start Streaming" in the app
2. Tap the AI button for voice + vision conversation

---

Quick Start (Android)

1. Clone and open

git clone https://github.com/sseanliu/VisionClaw.git

Open samples/CameraAccessAndroid/ in Android Studio.

2. Configure GitHub Packages (DAT SDK)

The Meta DAT Android SDK is distributed via GitHub Packages. You need a GitHub Personal Access Token with read:packages scope.

1. Go to GitHub > Settings > Developer Settings > Personal Access Tokens and create a classic token with read:packages scope
2. In samples/CameraAccessAndroid/local.properties, add:

github_token=YOUR_GITHUB_TOKEN

Tip: If you have the gh CLI installed, you can run gh auth token to get a valid token. Make sure it has read:packages scope -- if not, run gh auth refresh -s read:packages.

Note: GitHub Packages requires authentication even for public repositories. The 401 error means your token is missing or invalid.

3. Add your secrets

cd samples/CameraAccessAndroid/app/src/main/java/com/meta/wearable/dat/externalsampleapps/cameraaccess/
cp Secrets.kt.example Secrets.kt

Edit Secrets.kt with your Gemini API key (required) and optional WebRTC config.

4. Build and run

1. Let Gradle sync in Android Studio (it will download the DAT SDK from GitHub Packages)
2. Select your Android phone as the target device
3. Click Run (Shift+F10)

Wireless debugging: You can also install via ADB wirelessly. Enable Wireless debugging in your phone's Developer Options, then pair with adb pair <ip>:<port>.

5. Try it out

Without glasses (Phone mode):

1. Tap "Start on Phone" -- uses your phone's back camera
2. Tap the AI button (sparkle icon) to start a Gemini Live session
3. Talk to the AI -- it can see through your phone camera

With Meta Ray-Ban glasses:

Enable Developer Mode in the Meta AI app (same steps as iOS above), then:

1. Tap "Start Streaming" in the app
2. Tap the AI button for voice + vision conversation

---

Architecture

Key Files (iOS)

All source code is in samples/CameraAccess/CameraAccess/:

File	Purpose
Gemini/GeminiConfig.swift	API keys, model config, system prompt
Gemini/GeminiLiveService.swift	WebSocket client for Gemini Live API
Gemini/AudioManager.swift	Mic capture (PCM 16kHz) + audio playback (PCM 24kHz)
Gemini/GeminiSessionViewModel.swift	Session lifecycle, transcript state
iPhone/IPhoneCameraManager.swift	AVCaptureSession wrapper for iPhone camera mode
WebRTC/WebRTCClient.swift	WebRTC peer connection + SDP negotiation
WebRTC/SignalingClient.swift	WebSocket signaling for WebRTC rooms

Key Files (Android)

All source code is in samples/CameraAccessAndroid/app/src/main/java/.../cameraaccess/:

File	Purpose
gemini/GeminiConfig.kt	API keys, model config, system prompt
gemini/GeminiLiveService.kt	OkHttp WebSocket client for Gemini Live API
gemini/AudioManager.kt	AudioRecord (16kHz) + AudioTrack (24kHz)
gemini/GeminiSessionViewModel.kt	Session lifecycle, UI state
phone/PhoneCameraManager.kt	CameraX wrapper for phone camera mode
webrtc/WebRTCClient.kt	WebRTC peer connection (stream-webrtc-android)
webrtc/SignalingClient.kt	OkHttp WebSocket signaling for WebRTC rooms
settings/SettingsManager.kt	SharedPreferences with Secrets.kt fallback

Audio Pipeline

• Input: Phone mic -> AudioManager (PCM Int16, 16kHz mono, 100ms chunks) -> Gemini WebSocket
• Output: Gemini WebSocket -> AudioManager playback queue -> Phone speaker
• iOS iPhone mode: Uses .voiceChat audio session for echo cancellation + mic gating during AI speech
• iOS Glasses mode: Uses .videoChat audio session (mic is on glasses, speaker is on phone -- no echo)
• Android: Uses VOICE_COMMUNICATION audio source for built-in acoustic echo cancellation

Video Pipeline

• Glasses: DAT SDK video stream (24fps) -> throttle to ~1fps -> JPEG (50% quality) -> Gemini
• Phone: Camera capture (30fps) -> throttle to ~1fps -> JPEG -> Gemini

WebRTC Live Streaming

Share your glasses POV in real-time to a browser viewer with bidirectional audio and video.

1. Tap the Live button in the app
2. The app connects to a signaling server and gets a 6-character room code
3. Share the code -- the viewer opens the server URL in a browser and enters it
4. WebRTC peer connection is established (SDP + ICE via the signaling server)
5. Media flows peer-to-peer: glasses video to browser, browser camera back to iOS PiP

Key details:

• Signaling server: Node.js + WebSocket, located at samples/CameraAccess/server/ -- serves the browser viewer and relays SDP/ICE
• NAT traversal: Google STUN servers + ExpressTURN relay (fetched from /api/turn)
• Video: 24 fps, 2.5 Mbps max bitrate
• Background handling: 60-second grace period for iOS app backgrounding -- room stays alive for reconnection
• Constraint: Cannot run simultaneously with Gemini Live (audio device conflict)

For full details, see samples/CameraAccess/CameraAccess/WebRTC/README.md.

---

Requirements

iOS

• iOS 17.0+
• Xcode 15.0+
• Gemini API key (get one free)
• Meta Ray-Ban glasses (optional -- use iPhone mode for testing)

Android

• Android 14+ (API 34+)
• Android Studio Ladybug or newer
• GitHub account with read:packages token (for DAT SDK)
• Gemini API key (get one free)
• Meta Ray-Ban glasses (optional -- use Phone mode for testing)

---

Troubleshooting

General

Gemini doesn't hear me -- Check that microphone permission is granted. The app uses aggressive voice activity detection -- speak clearly and at normal volume.

iOS-specific

"Gemini API key not configured" -- Add your API key in Secrets.swift or in the in-app Settings.

Echo/feedback in iPhone mode -- The app mutes the mic while the AI is speaking. If you still hear echo, try turning down the volume.

Android-specific

Gradle sync fails with 401 Unauthorized -- Your GitHub token is missing or doesn't have read:packages scope. Check local.properties for gpr.user and gpr.token. Generate a new token at github.com/settings/tokens.

Gemini WebSocket times out -- The Gemini Live API sends binary WebSocket frames. If you're building a custom client, make sure to handle both text and binary frame types.

Audio not working -- Ensure RECORD_AUDIO permission is granted. On Android 13+, you may need to grant this permission manually in Settings > Apps.

Phone camera not starting -- Ensure CAMERA permission is granted. CameraX requires both the permission and a valid lifecycle.

For DAT SDK issues, see the developer documentation or the discussions forum.

License

This source code is licensed under the license found in the LICENSE file in the root directory of this source tree.