This project provides an AI-powered Japanese sentence analyzer designed for Chinese learners. It leverages the Gemini 2.5 Flash model to offer deep syntactic analysis, part-of-speech tagging, pronunciation, and definitions, making Japanese comprehension more accessible.

How It Works

The analyzer utilizes Gemini 2.5 Flash for its core natural language processing tasks. It breaks down Japanese sentences, identifies grammatical components, and provides detailed explanations and definitions in Chinese. Key features include OCR for text extraction from images, Text-to-Speech (TTS) for audio pronunciation, and full sentence translation for bilingual understanding. The system is built with a streaming API for a smoother user experience.

Quick Start & Requirements

• Installation: Deploy via Vercel by forking the repository and setting environment variables.
• Prerequisites: A Gemini API Key is required. Custom API URLs and an optional access password can also be configured.
• Demo: An online demo is available, though it uses a free API key and may be unstable.
• Documentation: Deployment guides and feature descriptions are available within the repository.

Highlighted Details

• AI-driven syntactic analysis and part-of-speech tagging.
• OCR integration for image-based text analysis.
• Gemini TTS for audio playback of Japanese text.
• Configurable access control and API endpoints.

Maintenance & Community

The project is licensed under the MIT License. Contributions are welcomed via GitHub Issues and Pull Requests. Contact is primarily through GitHub Issues.

Licensing & Compatibility

MIT License. This license is permissive and generally compatible with commercial use and closed-source applications.

Limitations & Caveats

The online demo uses a free, potentially unstable API key. The project currently only supports Gemini models, with potential for future expansion.