In‑Place Android Screen Translator (ALST)

说明与用途

ALST 是一款 Android 应用，可在实时翻译任何屏幕时，将翻译文本直接覆盖在原始内容上，无需离开当前应用。它使用 Gemini 3.6 Flash 进行云端翻译，ML Kit 支持离线模式，解决内存泄漏问题，并与系统 UI 集成。

问题

Mobile users struggle with language barriers because existing screen‑translation tools require screenshots, freeze screens, or overlay blocking text cards.

结果

ALST delivers seamless, real‑time translation directly over app content, improving contextual accuracy with Gemini and maintaining 100% offline capability via ML Kit, all while preventing memory leaks on Android 14+.

工作流

• 1. Capture screen frames via MediaProjection and ImageReader
• 2. Send bitmap to Gemini 3.6 Flash (cloud) or ML Kit OCR (offline)
• 3. Receive translated text and bounding boxes
• 4. Scale coordinates to device density and insets
• 5. Render glassmorphic overlay cards with Compose Canvas
• 6. Provide Quick Settings tile and floating FAB for quick activation

证据

ALST is built following Clean Architecture and MVVM/MVI design patterns.

来源

Gemini extracts the text, understands local context/idioms, and returns both the translated text and exact bounding box coordinates (Rect).

来源

Capturing raw 1440p / 4K screen frames produces bitmaps that consume over 15MB–20MB of RAM per frame.

来源