Shifty/Mastermind
1
1
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

Implement Push-to-Talk feature and enhance audio input settings in AssistantView and CustomizeView. Update README for API key instructions and improve audio processing logic in OpenAI SDK. Adjust pnpm-lock.yaml for dependency updates.

Browse Source
This commit is contained in:
Илья Глазунов
2026-01-16 00:41:58 +03:00
parent 669c019fd8
commit 656e8f0932
10 changed files with 5190 additions and 4095 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+18 -20
View File
@@ -1,10 +1,5 @@
<img width="1299" height="424" alt="cd (1)" src="https://github.com/user-attachments/assets/b25fff4d-043d-4f38-9985-f832ae0d0f6e" />
## Recall.ai - API for desktop recording
If you’re looking for a hosted desktop recording API, consider checking out [Recall.ai](https://www.recall.ai/product/desktop-recording-sdk/?utm_source=github&utm_medium=sponsorship&utm_campaign=sohzm-cheating-daddy), an API that records Zoom, Google Meet, Microsoft Teams, in-person meetings, and more.
This project is sponsored by Recall.ai.
<!-- <img width="1299" height="424" alt="cd (1)" src="https://github.com/user-attachments/assets/b25fff4d-043d-4f38-9985-f832ae0d0f6e" /> -->
# Mastermind
---
@@ -14,33 +9,36 @@ This project is sponsored by Recall.ai.
> [!NOTE]
> During testing it wont answer if you ask something, you need to simulate interviewer asking question, which it will answer
A real-time AI assistant that provides contextual help during video calls, interviews, presentations, and meetings using screen capture and audio analysis.
A real-time AI assistant that provides contextual help during video calls, interviews, presentations, and meetings using screen capture and audio analysis. It is fork of [Cheating Daddy](https://github.com/sohzm/cheating-daddy) project.
## Features
- **Live AI Assistance**: Real-time help powered by Google Gemini 2.0 Flash Live
- **Live AI Assistance**: Real-time help powered by Gemini API / OpenAI SDK / OpenAI Realtime API, so you can choose which one you want to use
- **Screen & Audio Capture**: Analyzes what you see and hear for contextual responses
- **Multiple Profiles**: Interview, Sales Call, Business Meeting, Presentation, Negotiation
- **Transparent Overlay**: Always-on-top window that can be positioned anywhere
- **Transparent Overlay**: Always-on-top window that can be positioned anywhere, if something goes wrong you can hide it without stoping session and losing context!
- **Click-through Mode**: Make window transparent to clicks when needed
- **Cross-platform**: Works on macOS, Windows, and Linux (kinda, dont use, just for testing rn)
## Setup
1. **Get a Gemini API Key**: Visit [Google AI Studio](https://aistudio.google.com/apikey)
2. **Install Dependencies**: `npm install`
3. **Run the App**: `npm start`
1. **Get a API Key**: Visit [Google AI Studio](https://aistudio.google.com/apikey) or [OpenAI](https://platform.openai.com/docs/api-reference) or any other OpenAI-compatible API!
2. **Install Dependencies**: `pnpm install`
3. **Run the App**: `pnpm start`
## Usage
1. Enter your Gemini API key in the main window
1. Enter your API key in the main window, select provider and model you want to use in preferences
2. Choose your profile and language in settings
3. Click "Start Session" to begin
4. Position the window using keyboard shortcuts
5. The AI will provide real-time assistance based on your screen and what interview asks
3. Click "Start Session" to begin, if you want to use push-to-talk mode, you can enable it in preferences
4. Position the window using keyboard shortcuts, or use your mouse to move it
5. The AI will provide real-time assistance based on your screen and system audio/microphone input, you can also send text messages to AI by pressing Enter
## Keyboard Shortcuts
> [!NOTE]
> All keyboard shortcuts are customizable in settings. You can check some default shortcuts below.
- **Window Movement**: `Ctrl/Cmd + Arrow Keys` - Move window
- **Click-through**: `Ctrl/Cmd + M` - Toggle mouse events
- **Close/Back**: `Ctrl/Cmd + \` - Close window or go back
@@ -48,13 +46,13 @@ A real-time AI assistant that provides contextual help during video calls, inter
## Audio Capture
- **macOS**: [SystemAudioDump](https://github.com/Mohammed-Yasin-Mulla/Sound) for system audio
- **Windows**: Loopback audio capture
- **macOS**: [SystemAudioDump](https://github.com/Mohammed-Yasin-Mulla/Sound) for system audio capture, you can use microphone input as well
- **Windows**: Loopback audio capture, you can use microphone input as well
- **Linux**: Microphone input
## Requirements
- Electron-compatible OS (macOS, Windows, Linux)
- Gemini API key
- AI Provider API key
- Screen recording permissions
- Microphone/audio permissions