Bayān: Touch Grass with open-source AI and local Arabic reflection

Описание и применение

Bayān – локальное приложение для практики арабской риторики, которое поощряет выйти из экрана, наблюдать окружающий мир и использовать локальные модели AI для создания более выразительных фраз.

Задача

Users want a low-friction way to practice Arabic imagery, sensory language, and thoughtful observation without relying on cloud AI services or complex interfaces.

Результат

Bayān provides a minimal, privacy-preserving, offline-capable experience that turns a short outdoor walk into a focused reflective writing task, supporting Arabic imagery and sensory language.

Рабочий процесс

• Select a rhetorical exercise (simile, metaphor, or sensory description).
• Step outside and observe a detail in the environment.
• Return to the app and use the local AI to transform the observation into a stronger Arabic phrase. (Optional: use local speech synthesis or transcription.)
• Write or record the final reflection. (Fallback behavior ensures a coherent experience if the model is unavailable.)

Доказательства

Bayān is a local-first Arabic rhetoric companion that gets people off the screen and back into the world.

Источник

The project uses: Ollama with Gemma 3 4B for mission generation, translation, and chat; FastAPI for the backend service layer; a lightweight static web frontend for the game flow; browser-local storage for lightweight game state; optional local Piper speech synthesis for Arabic playback; optional local Whisper transcription for voice-note input.

Источник

The app also includes validation and fallback behavior so that if the local model is unavailable or returns weak output, the user still receives a coherent experience instead of a broken UI.

Источник