🎙️ Arty - iOS realtime voice assistant w/ translation + connectors
Features
- Realtime Voice Assistant, fully interruptible
- Realtime Translator/Interpreter mode, including bi-directional translations.
- Extensions/connectors: DeepWiki MCP, Google Drive, GitHub, Hugging Face Papers, Hacker News, Web Search
- Generic MCP connector (experimental, still WIP)
- Works with 🔈 speaker or 🎧 headphones
- Customizable prompts: Edit system and tool prompts directly from the config UI
Tech Stack
- WebRTC
- Native Swift w/ echo cancellation support
- Expo / React Native
- OpenAI
gpt-realtimefor voice assistant mode gpt-realtime-translatefor translation mode
Requirements
- iOS - tested on ios 26, may work on earlier versions
- Bring Your Own OpenAI API Key
📱 Screenshots
▶️ Install it via TestFlight
Security note: TestFlight builds are compiled binaries; do not assume they exactly match this source code. If you require verifiability, build from source and review the code before installing.
🔐 Security + Privacy
Privacy status: Currently, the app uses OpenAI's API, which means user prompts and connector content are transmitted to OpenAI by design. Your credentials (API keys, OAuth tokens) never leave your device and are stored securely in iOS Keychain. Future updates will add support for self-hosted and fully local execution options.
🛠️ Building from source
Clone project and install dependencies
git clone https://github.com/vibemachine-labs/arty.git
cd arty
curl -fsSL https://bun.sh/install | bash
bun install
Run the app
To run in the iOS simulator:
bunx expo run:ios
⛓️💥 If you get CommandError: No iOS devices available in Simulator.app, it means you need to install the iOS platform in Xcode. Go to Xcode > Settings > Components and install the iOS platform.
⚠️ Audio is flaky on the iOS Simulator. Using a real device is highly recommended.
To run on a physical device:
bunx expo run:ios --device
Open Xcode project
To open the project in Xcode:
xed ios
In Xcode, the native swift code will be under Pods / Development Pods
Create a Google Drive Client ID (Optional)
When building from source, you will need to provide your own Google Drive Client ID. You can decide the permissions you want to give it, as well as whether you want to go through the verification process.
For testing, the following oauth scopes are suggested:
- See and download your google drive files (included by default)
- See, edit, create, and delete only the specific Google Drive files you use with this app
Development notes
- Project bootstrapped with
bunx create-expo-app@latest . - Refresh dependencies after pulling new changes:
bunx expo install - Install new dependencies:
bunx expo install <package-name> - Allow LAN access once:
bunx expo start --lan
Run on iOS device via ad hoc distribution
- Register device:
eas device:create - Scan the generated QR code on the device and install the provisioning profile via Settings.
- Configure build:
bunx eas build:configure - Build:
eas build --platform ios --profile dev_self_contained
Clean build
If pods misbehave, rebuild from scratch:
bunx expo prebuild --clean --platform ios
bunx expo run:ios
📦 Expo Build
Additional Deps
brew install fastlane
Expo login
bunx eas login
Setup Apple Dev Account
bunx eas credentials
Run build wizard
bun run wizard
⚙️ Technical Details
Native Swift WebRTC Client
React Native WebRTC libraries did not reliably support speakerphone mode during prototyping. The native Swift implementation resolves this issue but adds complexity and delays Android support.
Connector Architecture
All connectors use statically defined tools with explicit function definitions, providing reliability and predictable behavior. Examples include Google Drive file operations, DeepWiki documentation search, Hacker News browsing, and Daily Hugging Face Top Papers discovery.
MCP Support
MCP (can be enabled in settings): Connects to external MCP servers via a streamable HTTP endpoint.
Note: OAuth token refresh is implemented but still very buggy.
Web Search
GPT-4 web search serves as a temporary solution. The roadmap includes integrating a dedicated search API (e.g., Brave Search) using user-provided API tokens.
Voice / Text LLM backend
OpenAI is currently the only supported backend. Adding support for multiple providers and self-hosted backends is on the roadmap.
📬 Contact & Feedback
- Email/Twitter: Email or Twitter/X via my Github profile.
- Issues, Ideas: Submit bugs, feature requests, or connector suggestions on GitHub Issues.
- Responsible disclosure: Report security-relevant issues privately via email using the address listed on my Github profile before any public disclosure.
No comments yet
Be the first to share your take.