About CharaStudio

CharaStudio is a desktop app focused on AI character creation and Desktop Buddy companions, bringing character generation, immersive chat, and an always-on desktop companion into one unified platform. We believe AI should not just be a tool, but a vivid, warm presence right on your desktop.

Whether you want to craft unique AI characters, hold deep conversations with them, or have a companion by your side while you work, CharaStudio delivers an experience that is both fluid and professional.

Our mission is to make AI character creation and companionship accessible to everyone — intuitive, emotional, and high-quality. We believe the best AI experiences should be within reach, full of personality, and crafted with care.

• AI Character Creation / Chat — Generate characters with natural language and chat with them directly
• Desktop Buddy — Bring your characters onto your desktop as always-on companions
• Cross-Platform — Available on Windows, macOS, and Linux
• Multi-Language — Supports Chinese, English, Japanese, Korean, Arabic, and Turkish interfaces
• Multi-Model Support — Integrates mainstream AI models from OpenAI, Google, MiniMax, and more

CharaStudio is a premium digital studio focused on character and story creation. All core features of our platform are publicly maintained on GitHub, and we welcome feedback and suggestions from users who share our vision.

CharaStudio is built by a distributed team of developers, designers, and AI researchers who are passionate about creative technology. We are committed to ensuring our tools reflect the needs and values of creators worldwide.

There are many ways to get involved with CharaStudio:

For general inquiries, bug reports, or feature requests, please open an issue on our GitHub repository. We welcome contributions from the community and are always looking for feedback on how to improve CharaStudio.

CharaStudio's core functionality relies on advanced third-party AI models. Below are the main models we currently use and their access sources:

Large Language Models (LLM)

We use the following large language models for conversation, story generation, and other features:

• OpenAI GPT Series: GPT-4o, GPT-4o-mini, GPT-4-Turbo, etc.
• Google Gemini Series: Gemini-1.5-Pro, Gemini-1.5-Flash, Gemini-2.0-Flash, etc.
• MiniMax Series: MiniMax-M2.5, MiniMax-M2.7, MiniMax-M3, etc.

Image Generation Models

We use the following image generation models:

GPT-Image-2 (OpenAI), NanoBanana-2, etc.

Model Access Sources

Our AI models are accessed through the following reliable third-party service providers:

• OpenRouter: Provides a unified AI model access interface, integrating resources from multiple model providers
• SiliconFlow: Provides stable AI API services, supporting various mainstream models
• MiniMax Official: Direct access to MiniMax official API services

Note

We may adjust the specific model versions and access sources from time to time based on service requirements and technological developments. All AI content generated through official interfaces undergoes security review to ensure content compliance.