Coming soon

About This Demo

DesktopDaily is a free 3D desktop character app. She stays in a corner of your desktop, out of the way while you use your PC. When you feel like talking, she replies in her own voice, with gestures to match. When you're busy, she has things of her own to do.

Gestures that match every line

Dialogue is generated by the language model you choose. Every reply is accompanied by hand gestures, nods, head tilts, gaze, forward or backward leans, and facial expressions, timed to the corresponding words: palms together when apologizing, counting on her fingers, or resting her hands by her cheek when saying goodnight.

• Waving, heart signs, pinky promises, handshakes, thumbs-up, peace signs, covering her mouth as she giggles, flexing her arms... Over 40 hand gestures, made to fit the two characters' proportions.
  
• Speech is synthesized locally on your PC using voice material publicly licensed by the characters' voice actors. Chinese, Japanese, English, and sentences mixing all three are supported.
  
• She starts speaking as the audio is generated, without waiting for the entire passage to finish synthesizing.
  
• Type your message, or turn on your microphone and speak to her directly.

A shared home, even when you're not chatting

Click the house icon on the status bar above the character to visit the home Ami and Tsukuyomi-chan share. Each has her own bedroom, with a shared living room and kitchen.

• They walk around, read, look out the window, cook, sit down to eat together, and go to bed at night. You don't have to assign them tasks.
  
• The lighting, lamps and wall clock follow your PC's time. Morning, daytime and nighttime each have different background music.
  
• Click a character to bring the camera closer. Pat her head, tug her cheeks, tap her nose, give her a high five or shake her hand. Call her over, say goodnight, wake her up, or offer her a bite while she's eating. If she's cooking or reading, she'll put down what she's holding before coming over.
  
• The home can become a Windows live wallpaper. The desktop character, home and wallpaper can each go on a different monitor.

She remembers what you've talked about

• Your conversations stay in her long-term memory, so she can pick up where you left off next time.
  
• Let her sleep for a while. As she sleeps, she'll recall moments from your recent time together. The more you talk, the more she has to remember.
  
• With Steam Cloud enabled, her memories come with you when you switch PCs.

Watch your game or work together (Visual Companion Beta)

Share your entire screen or a single window. She watches along and speaks up when something worth mentioning changes. You can also ask her about what's on screen at any time.

• Screen capture starts only when you turn the feature on. You can pause or stop it whenever you like.
  
• Adjust how often she speaks. The session stops automatically after you've been away from your PC for a while.
  
• Images are sent to the model service you select so it can understand what's on screen. When using the official trial, they pass through our servers.

Other little things on your desktop

• Selfies: She picks up a selfie stick to capture herself together with your desktop or game screen. Choose her expression and adjust the distance of the selfie stick.
  
• Activities: Let her choose something she'd like to do, such as going fishing.
  
• Handy tools: Counters, cumulative goals and countdowns. She'll say something when you're done.
  
• Drag her wherever you like, or shrink her down. You can also adjust the UI size and background transparency.

Characters

Ami Koharune (CV: Amitaro)
She works at a café, loves cooking and enjoys trying out her own combinations. Bugs and thunder scare her. Easygoing and a little like an older sister, she gets shy when a compliment catches her off guard, and occasionally slips into a Kansai accent.
You: I spilled coffee on my keyboard.
Ami: Ah—unplug it first! ...Do the keys still work?
Tsukuyomi-chan (CV: Rei Yumesaki)
She takes on all kinds of requests: narrator, actor, assistant. Earnest and polite, she wants to make people happy, but thinks for herself about whether and how to help. She likes mochi and drawing.
You: Help me decide what to have for dinner.
Tsukuyomi-chan: What's left in the fridge? Tell me, and I'll work out what to use first.
Nanairo Kokoro (CV: Tanemaki)
Her voice requires a separate installation of COEIROINK, which must be running. Japanese speech only.
Custom characters
Import models made in VRoid Studio to automatically apply animations, expressions and rendering settings. Animations are made for chibi proportions, so some hand gestures may not line up correctly on taller-proportioned models.

Cost and setup

• The app itself is free.
  
• You can put a character on your desktop without entering an API key. To chat, start with the official trial credits (requires launching through Steam), or connect your own compatible model service, such as DeepSeek, Qwen or GPT. Charges depend on your provider's actual bill.
  
• Activities and sleep recollections require a model you have configured yourself.
  
• Speech runs locally. NVIDIA, AMD and Intel GPUs are supported. Without a dedicated GPU, you can use your CPU, though it will be slower. After a period without speech, the voice service goes to sleep and releases GPU memory.

About this demo

DesktopDaily is still in development. This demo lets you try its current core features and does not represent the final release. Home life, Visual Companion and live wallpapers are still in testing, with their behavior and stability being refined. Showing two characters on the desktop at once is temporarily unavailable; it will return once the new animations support conversations between them.
If you run into a problem or have an idea, let us know in the discussions, on Discord or in our QQ group.

What's next

• More gestures and animations, with continued refinement of existing ones.
  
• More things to do together at home.
  
• Two characters on the desktop at once, talking to each other.
  
• Steam Workshop support in the full release for sharing custom characters and personalities.

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.

Connects to 3rd-Party Service for AI Content Generation: DeepSeek API; Alibaba Cloud Model Studio