{"slug": "how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app", "title": "How I Built ALAD Mobile: Real-Time AI Audio Dubbing for Any Android App", "summary": "A developer has built ALAD Mobile, an open-source native Android application that captures internal system audio in real-time, streams it through Google's Gemini Multimodal Live API, and instantly plays back translated voice over any active media. The app uses Android's MediaProjection API for audio capture, a persistent WebSocket connection to Gemini's Live API for low-latency translation, and a floating overlay widget for seamless control. It is free and open source, requiring only a free API key from Google AI Studio.", "body_md": "Have you ever wanted to watch a foreign YouTube video, a live stream on Twitch, or a show on Netflix without constantly staring at subtitles?\n\nTo solve this, I built **ALAD Mobile** (Live Audio Dubbing) — an open-source native Android application that captures internal system audio in real-time, streams it through Google's **Gemini Multimodal Live API**, and instantly plays back the translated voice over any active media.\n\nALAD Mobile creates a system-wide floating overlay widget that sits comfortably over your active applications. Once activated:\n\nBuilding low-latency real-time voice translation on mobile required a carefully structured stack:\n\n`StateFlow`\n\n, and `SharedFlow`\n\n`MediaProjection`\n\n/ `AudioRecord`\n\nfor internal audio capture + `AudioTrack`\n\nfor low-latency playback`TYPE_APPLICATION_OVERLAY`\n\nUsing Android's `MediaProjection`\n\nAPI and `AudioRecord`\n\n, the app captures raw PCM audio streams from the device's internal sound engine without relying on external microphone input.\n\nTraditional REST API requests introduce too much latency for live translation. ALAD Mobile opens a persistent WebSocket connection directly to Gemini's Live API, continuously streaming PCM audio chunks in real-time.\n\nAs Gemini processes and translates the stream, incoming audio payloads are decoded and pushed directly into a low-latency `AudioTrack`\n\nbuffer for smooth, near-instant voice playback.\n\nTo ensure zero friction, a Floating Control Widget built with Android's System Alert Window lets users control dubbing and switch target languages seamlessly over any running app.\n\n`StateFlow`\n\n.ALAD Mobile is **100% Free and Open Source**. It runs using a free API key directly from [Google AI Studio](https://aistudio.google.com/) — no subscriptions or user accounts required.\n\nIf you find this project interesting, feel free to drop a ⭐ star on GitHub, submit a PR, or leave your architectural feedback below!", "url": "https://wpnews.pro/news/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app", "canonical_source": "https://dev.to/navidseyedain/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app-4b9", "published_at": "2026-08-11 01:07:52+00:00", "updated_at": "2026-08-11 01:46:08.821620+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-products", "ai-tools", "developer-tools"], "entities": ["ALAD Mobile", "Google", "Gemini Multimodal Live API", "Android", "MediaProjection", "AudioTrack", "Google AI Studio", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app", "markdown": "https://wpnews.pro/news/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app.md", "text": "https://wpnews.pro/news/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app.txt", "jsonld": "https://wpnews.pro/news/how-i-built-alad-mobile-real-time-ai-audio-dubbing-for-any-android-app.jsonld"}}