Free and open source · Linux · macOS · Windows

Your desktop, with a buddy on it.

Shika AI is a small pet companion that lives on your screen. Hold a key and talk, and your words are typed into any app. It also keeps your reminders and barks when one is due.

Speech is turned into text on your own computer. Nothing is sent to a server. Also known as Desktop Buddy.

What it does

Four small jobs, done by a buddy.

Talk, and it types.

Hold Right Ctrl, speak, let go. The text lands at your cursor in whatever app you are using. No account and no internet needed after the first model download.

Your words will appear here.
Press and hold the button. Use Space or Enter on a keyboard.

Say a command.

Hold Right Alt (Right Option on a Mac) and say what you want.

open firefoxclose tablock screenvolume upsearch DV360 line item setupbe a pandacall yourself Momo

Reminders that bark.

Say "remind me at 5 to call Rahul". At 5 the buddy runs to the middle of your screen and barks. Tap it to mark the reminder done, double-tap to snooze 10 minutes.

Fix text by voice.

Select text in any app, hold the command key and say "fix grammar" or "make it shorter". A small model running on your own machine rewrites it and pastes it back. Ctrl+Z undoes it. This part is optional and needs Ollama.

Shika AI

AI that runs on your own computer.

Shika AI uses two small models. Both run locally, so your voice and your text are not sent to any company's server. You can swap either one for a model you like better.

Speech model

Included

Turns your voice into text. It uses faster-whisper with the small.en model. The installer downloads it, about 500 MB, and it runs on your CPU.

Language model

Asked at install

Cleans up what you said and edits selected text. It uses Ollama with qwen2.5:1.5b, about 1 GB. The installer asks if you want it, and the default answer is yes.

Your choice of model

One line to change

Use a bigger, smaller or multilingual model. Change one name in the program file and restart. The setup guide shows each step.

Change the model

What Shika AI does with your words

  • Fixes grammar, spelling, punctuation and capital letters.
  • Removes filler words such as "um" and "you know".
  • Follows your self-corrections. "At 4, no wait, 5" becomes "5".
  • Turns spoken punctuation like "comma" and "new line" into the real thing.
  • Puts a spoken list on separate lines.
  • Keeps your language. Hinglish stays Hinglish.

A typical result

You say

um so remind me at 4 no wait 5 to call Rahul comma and send the invoice

Shika AI types

Remind me at 5 to call Rahul, and send the invoice.

Results depend on the model you pick. This is an example, not a promise for every sentence.

No language model? It still works.

Dictation, commands, reminders and widgets do not need it. Without it, Shika uses quick rule based cleanup. Voice edits like "make it shorter" and "fix grammar" do need the language model.

# change these two lines in shika.py, then restart
WHISPER_MODEL = "small.en"      # speech to text
OLLAMA_MODEL  = "qwen2.5:1.5b"  # text cleanup and edits
How it works

From your voice to typed text in four steps.

  1. Hold the key. Hold Right Ctrl to dictate, or Right Alt (Right Option on a Mac) for a command.
  2. Speak. The buddy listens through your microphone. Nothing is recorded to a file.
  3. Your computer transcribes. The speech model turns the audio into text without using the internet.
  4. The text appears. If the language model is on, it tidies the text first. Then it is typed where your cursor is, in any app.
Characters

Fifteen buddies. You pick the name.

Three pups and twelve other pet companions, each drawn in code with its own moods. Pick one below and the buddy at the bottom of this page changes with it. Every character keeps its own name.

Widgets

Small windows for the things you check all day.

Tasks, sticky notes, a focus timer and a clock. They float on your desktop, remember where you left them, and work the same on Linux, macOS and Windows. These are live samples.

TASKS & REMINDERS
  • Upload session recording
  • Send invoice
  • Call Rahul · 5:00 PM
STICKY NOTE
FOCUS TIMER
25:00
CLOCK

On Linux with KDE Plasma you can also use the same widgets as native Plasma widgets. Both read and write the same files.

Platforms

One app, three systems.

Linux is where it was built and tested every day. The Mac and Windows versions came later and have only been tested with simulated keyboards and windows, not on real machines yet. Please report what breaks.

Linux

Tested daily

Kubuntu with KDE Plasma 6. Installer uses apt. Plasma widgets included.

Linux guide

macOS

Early, untested on real Macs

Needs Microphone, Input Monitoring and Accessibility permissions once.

Mac guide

Windows 10 and 11

Early, untested on real PCs

One installer. Start Menu entry and start at sign-in.

Windows guide
Good for

People who write a lot and type a little less.

Writers and marketers

Dictate emails, captions and drafts. The cleanup step removes the "ums" and fixes the punctuation for you.

Students and teachers

Speak notes while you read. Keep tasks and reminders on the desktop, with a focus timer next to them.

Developers and power users

Dictate comments and messages, open apps and close tabs by voice, and read or change the code. It is one Python file.

Compared

Shika AI and typical cloud dictation.

Shika AITypical cloud dictation
Where your voice goesStays on your computerSent to a server
Works offlineYes, after setupUsually no
Account neededNoUsually yes
PriceFree, MIT licenseOften a subscription
Choose your own modelYesNo
Source codeOpenClosed
Accuracy on hard audioGood, depends on the model you pickOften better on very noisy audio
Install

Three commands, then say hi.

You need Python 3.10 or newer on Mac and Windows. The first run downloads a speech model of about 500 MB. The installer then asks if you want Shika AI, the language model, which is about 1 GB more. Add --no-ai to skip the question.

git clone https://github.com/iam-knr/desktop-buddy.git
cd desktop-buddy
bash install.sh

Log out and back in once so push-to-talk can read your keyboard.

Open the full setup guide

Questions

Before you install it.

What is Shika AI?

Shika AI is a free, open source desktop companion and offline voice assistant for Linux, macOS and Windows. A small pet companion lives on your screen. You hold a key, speak, and your words are typed into the app you are using. It also keeps reminders, notes and a focus timer.

Is Shika AI the same as Desktop Buddy?

Yes. Desktop Buddy is the earlier name of the same project. The pup that walks on your screen is called Shika by default, and you can rename it.

Do I get the AI when I download it?

You always get the speech model, which turns your voice into text. The installer downloads it, about 500 MB. The language model that tidies your text is asked about during install, and the default answer is yes. It is about 1 GB. You can skip it with the no-ai option and add it later.

Is my voice sent anywhere?

No. Speech recognition and the language model both run on your computer. The only downloads are the model files, once.

Does it work without internet?

Yes, after the first install and model download. Dictation, commands, reminders and widgets all work offline.

How do I change the AI model?

Open the program file, find OLLAMA_MODEL for the language model or WHISPER_MODEL for the speech model, change the name, and restart. The setup guide has the exact steps, a list of good models and what each one costs in size and speed.

Which model is best for a slow computer?

Keep the defaults, or use base.en for speech and a 1B language model. A bigger model is smarter but slower on a CPU. If the language model is too slow, Shika gives up after a few seconds and uses basic cleanup instead.

Which languages does it understand?

English by default. You can switch to a multilingual speech model and set the language, or leave it on auto. Hindi and Hinglish text is kept as you speak it. Languages other than English have had much less testing.

Does it need a graphics card?

No. Both models run on the CPU. A graphics card is not needed.

Is it free?

Yes. It is open source under the MIT license. You can read the code, change it and share it.

Can I add my own character?

Yes. Characters are plain entries in one list in the program file. Copy one and change the colors, ears, tail and face.

Kailas (KNR) Nath R at his laptop
Made by

Kailas (KNR) Nath R

Agentic AI Consultant, Digital Marketing Trainer and Developer. India.

I run ads for brands, build AI agents that handle the boring parts of marketing, and teach both. I built Shika because I wanted a desktop buddy that could also type for me.

Built with Monster Energy Zero Ultra can &