About This Game

About This App

DesktopDaily is designed to let 3D characters become a more natural part of your everyday desktop.

The design focus is not on affection points or relationship stats. Instead, we want to create a sense of continuous desktop companionship: a character stays on your computer desktop and gradually becomes part of your everyday environment while you work, study, browse, or take a break.

You do not need to constantly interact with the character or give them your full attention. They can stay quietly in a corner of your desktop and react from time to time. When you want to talk, you can use your own API key to chat with the character, and the reply can be played back through local voice synthesis.

DesktopDaily is about the everyday moments you share with a character on your desktop.

Core Experience in Development

3D characters on your desktop

Characters are displayed through a transparent window, making them suitable for staying on your desktop during everyday computer use. You can place them in a corner of the screen without entering a traditional game window.

Basic desktop interaction

The current version provides character display, position adjustment, scaling, hiding, and basic settings, allowing characters to fit more naturally into your desktop environment.

Conversation

You can talk with the character by configuring a compatible API key. Conversation text is generated by the model selected by the user. The current version does not include a built-in cloud LLM service.

Local voice synthesis

Character replies can be played back through local TTS. Voice synthesis runs on the user's own device and is not provided as a cloud TTS service. Actual speed and performance may vary depending on CPU, GPU, driver, and inference method.

Selfie feature

The current version is testing a selfie feature. The character can pick up a selfie stick and appear together with the current desktop screen. You can adjust the selfie stick distance, switch expressions, and save a screenshot that includes both the character and your desktop.

This is not just an ordinary screenshot. We want it to capture the character, your desktop, and the moments you spend together.

Life simulation events

The app is developing life simulation event features, and the current version has already begun offering event experiences such as fishing. Characters may trigger small events on the desktop, such as fishing, cooking, resting, or showing items they have obtained.

These events are not simply auto-playing performances. Instead, we want you to be able to progress through events together with the character through conversation. For example, during an event, you can respond to the character, make choices, or continue chatting, and the character will react based on the current event state and your conversation.

Specific event content, trigger conditions, and presentation may continue to change based on development progress and test feedback.

Character detail viewing

The app is planned to include a way to view character model details more closely, such as hair ornaments, accessories, outfits, and other small decorations. We want the characters to feel like carefully made 3D characters staying on your desktop, not just images displayed on the screen.

Current Characters

The current test version includes the following characters:

• Free material character “Tsukuyomi-chan” (つくよみちゃん)
  
• Voice material character “Koharune Ami” (小春音アミ)

DesktopDaily is not an official work by the rights holders of the related characters. Characters, voice materials, and 3D model-related assets are credited and used according to their respective terms.

Complete credit and license information can be found in the app, in the included files, and on the credit page of the app's official website.

Public Playtest Plan

The current version is still in development and internal testing. Before opening it to the public, we will continue adjusting the basic experience and confirming the stability of the current build through limited previews and feedback.

After that, we plan to open a public test through Steam Playtest to verify:

• Performance on different hardware environments;
  
• Compatibility and speed of local TTS;
  
• Whether the API key setup process is clear;
  
• Stability of the transparent desktop window and basic interaction;
  
• The actual experience of in-development features such as the selfie feature and life simulation events;
  
• Areas where character motion, display, and overall user experience need improvement.

The public test build will not represent the final content. It is a development build for collecting feedback and gradually improving the experience.

Future Development Direction

DesktopDaily will continue to be improved in future versions. Planned development directions include:

• Memory features;
  
• Expansion of life simulation events;
  
• Additional motions and motion polish;
  
• Notification and reminder features;
  
• Expansion of photo and screenshot-related features;
  
• Voice input;
  
• Visual understanding;
  
• Optional local AI features;
  
• More character performances and desktop interactions.

These features will be added gradually depending on development progress, test feedback, and practical feasibility. Specific content may change during development.

AI Generated Content Disclosure

The developers describe how their game uses AI Generated Content like this:

About Art Assets

DesktopDaily does not use AI-generated artwork for its in-game art assets. Character designs, 3D models, textures, animations, UI assets, and other visual content are created by human artists or based on properly licensed materials.

About Character Voices and Speech Synthesis

DesktopDaily’s character voice models are trained or fine-tuned using voice materials with clear provenance and authorization, and are used for character speech synthesis at runtime. These voice materials come from publicly available or authorized audio materials provided by the corresponding character or voice provider, and are used in accordance with their usage terms and authorized scope.

The character voices played at runtime are synthesized speech and are not original voice recordings.

About the Use of Generative AI

During development, AI assistance was used for parts of the code implementation and for some non-Chinese UI text localization. At runtime, generative AI is used only in optional features, including the character conversation feature, the visual companion feature, and notification assistant tools.

Some non-Chinese UI text localization uses AI-assisted translation and editing. This is limited to UI text localization and is separate from the runtime generation of character dialogue.

In the optional character conversation feature, AI is used to generate character dialogue text and to synthesize speech based on that text. When this feature is enabled, player input may be sent to cloud AI services in order to generate character-style response text. These responses may also be used for speech synthesis and played back in the game. If the player chooses not to use an API, the character conversation feature will not be enabled, and only the basic features will be available.

In the optional visual companion feature, after the player actively enables the feature, the game may use a local vision-language model to analyze screen, window, or application content within the scope authorized by the player. The analysis results may be used as context for character dialogue, allowing the character to respond based on the player’s current computer usage scenario. This feature is disabled by default. If the analysis results are used in cloud-based character dialogue, necessary summary information may be sent as part of the dialogue context to the cloud AI service selected or configured by the player.

In the optional notification assistant tools, after the player actively enables the feature and grants permission, the game may read Windows system notifications, email summaries, or other information sources specified by the player. A local AI model may be used to filter, categorize, or judge the importance of this information in order to decide whether to notify the player. This feature is intended to assist with notification management, and will not reply to emails, send messages, or perform external actions on behalf of the player. AI-based classification and notification results may be inaccurate.

The official trial API provided by the game uses Alibaba Cloud Model Studio. Players may also configure other APIs themselves. When features that require cloud AI are enabled, the necessary conversation content or contextual information is sent directly to the corresponding cloud AI service and is not relayed through the developer’s own server.

Character dialogue generated by AI at runtime is intended only for everyday companion-style interaction. The game uses prompts, content rules, and safety measures to reduce the output of inappropriate, illegal, hateful, sexual, violent, or copyright-infringing content. AI-generated responses may vary and do not represent official statements by DesktopDaily, the game’s developer, any character rights holder, voice provider, or third-party asset creator.