Break language barriers instantly with AI-powered speech recognition and translation.

Install · Features · Tech Stack · Roadmap · Contributing

AsizweAI (meaning "Let Us Hear" in Zulu) is a Chrome extension that provides real-time translation of spoken vernacular, slang, and regional dialects into your preferred language. Whether you're watching a video, attending a virtual meeting, or consuming content in an unfamiliar dialect, AsizweAI captures the audio and delivers instant, context-aware translations.

Built with a focus on African languages (Zulu, Xhosa, Afrikaans) while supporting 15+ global languages, AsizweAI bridges communication gaps that traditional translators miss preserving cultural nuance, tone, and idiomatic expressions.

• Vernacular First: Unlike generic translators, we're optimized for colloquial speech, slang, and regional expressions
• Real-Time Processing: Hear translations as conversations happen, not after
• Privacy Focused: Audio is processed through secure APIs nothing is stored on our servers
• Cultural Preservation: Translations maintain the emotional intent and cultural context of the original speech

• Glassmorphism UI — Premium, modern interface inspired by Notion and Linear
• One-Click Activation — Start translating with a single button press
• Live Transcript — See original and translated text in real-time
• Copy to Clipboard — Export your transcript with one click
• Swap Languages — Quickly reverse translation direction
• Volume Controls — Independent control for original audio and translation voice

• WCAG 2.1 Compliant — Full keyboard navigation and screen reader support
• Reduced Motion Support — Respects user preferences for animations
• High Contrast Mode — Enhanced visibility for users who need it

┌─────────────────────────────────────────────────────────────────┐
│                        Chrome Extension                          │
├─────────────────────────────────────────────────────────────────┤
│  Popup UI          │  Service Worker      │  Offscreen Document │
│  ───────────       │  ───────────────     │  ─────────────────  │
│  • Controls        │  • Message Router    │  • Audio Capture    │
│  • Transcript      │  • Tab Capture       │  • STT Processing   │
│  • Settings        │  • State Management  │  • Translation      │
│                    │                      │  • TTS Playback     │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
              ┌───────────────────────────────┐
              │         External APIs          │
              ├───────────────────────────────┤
              │  OpenAI · Deepgram · ElevenLabs │
              └───────────────────────────────┘

• Google Chrome (v88 or later)
• An API key from one of the following:
  • OpenAI (recommended)
  • Deepgram (free $200 credits)
  • ElevenLabs (best for African languages)

1. Clone the repository

   git clone https://github.com/yourusername/asizwe-ai.git
   cd asizwe-ai

2. Open Chrome Extensions

   Navigate to chrome://extensions in your browser

3. Enable Developer Mode

   Toggle the "Developer mode" switch in the top-right corner

4. Load the extension

   Click "Load unpacked" and select the asizwe-ai folder

5. Configure API Keys

   • Click the AsizweAI icon in your toolbar
   • Click the settings (gear) icon
   • Enter your API key(s)
   • Select your preferred providers
   • Click "Save Settings"

6. Start translating!

   Navigate to any page with audio, click the AsizweAI icon, and press the microphone button

Coming soon! The extension is currently in review.

1. Navigate to a page with audio content (YouTube, a meeting, etc.)
2. Click the AsizweAI extension icon
3. Select your source and target languages
4. Press the microphone button to start
5. View real-time transcripts and hear translations

• Real-time tab audio capture
• Multi-provider STT support
• GPT-powered translation
• Text-to-speech output
• Glassmorphism UI redesign
• Copy transcript to clipboard
• Swap languages functionality
• WCAG accessibility compliance

• Microphone Input — Translate your own speech in conversations
• Custom Vocabulary — Add slang/jargon specific to your context
• Conversation Mode — Bi-directional translation for dialogue
• Offline Mode — Local models for privacy-sensitive use cases
• Firefox Support — Cross-browser extension
• Mobile Companion — React Native app for on-the-go translation
• API Access — Developer API for integration into other apps
• Enterprise Features — Team management, usage analytics

• Sotho (Northern & Southern)
• Tswana
• Swahili
• Yoruba
• Hausa
• Amharic

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/amazing-feature)
3. Commit your Changes (git commit -m 'Add some amazing feature')
4. Push to the Branch (git push origin feature/amazing-feature)
5. Open a Pull Request

• Follow the existing code style (ES Modules, CSS Custom Properties)
• Ensure accessibility is maintained (test with screen readers)
• Add appropriate comments for complex logic
• Test with multiple STT/TTS providers

Distributed under the MIT License. See LICENSE for more information.

• OpenAI for Whisper and GPT models
• Deepgram for real-time speech recognition
• ElevenLabs for natural voice synthesis
• LibreTranslate for open-source translation
• The Chrome Extensions team for Manifest V3 documentation

AsizweAI — Let Us Hear
_{Built with purpose. Designed for connection.}

Report Bug · Request Feature