English

简体中文
繁體中文

English

简体中文
繁體中文

Appearance

Product Overview ​

CueMate is an open-source intelligent voice interview assistant - an AI-driven real-time interview training tool focused on helping job seekers improve their interview skills and performance through systematic mock interview training and preparation.

1. Product Positioning ​

CueMate is designed for job seekers who need to improve their interview abilities, especially those applying for technical positions. Through AI-driven mock interview systems, real-time speech recognition, intelligent answer generation, and knowledge base retrieval, it helps users fully prepare and systematically train before interviews.

IMPORTANT

Correct Ways to Use CueMate:

  • Pre-interview Preparation: Organize your knowledge base, prepare answers, and familiarize yourself with job requirements at your computer
  • Mock Interview Training: Use AI to simulate interviewers for repeated practice to improve interview skills
  • Post-interview Review: Review weaknesses after interviews for targeted improvement

2. Core Advantages ​

TIP

For detailed feature descriptions, please see the Core Features page.

2.1 Real-time Response ​

  • Low-latency Speech Recognition: Real-time speech-to-text based on CueMate-ASR, with speech-to-text latency under 200ms
  • Fast Answer Generation: LLM inference response time < 1.5 seconds
  • Streaming Output: Answers are displayed as they're generated, no waiting required

2.2 Intelligent and Accurate ​

  • Multi-model Support: Supports 24+ mainstream LLMs including OpenAI, Claude, Gemini, Zhipu GLM, Qwen, DeepSeek, Kimi, local models (Ollama, vLLM), etc.
  • User-customizable Model Selection: Custom models with unified API for simplified integration
  • RAG Enhancement: Combines personal resume, project experience, and interview questions for more relevant answers

2.3 Multi-language Support ​

  • Multi-language Interface: Supports Simplified Chinese, Traditional Chinese, and English
  • Multi-language Speech Recognition: ASR supports Chinese and English speech recognition
  • Document Localization: Complete multi-language documentation support

2.4 Easy to Use ​

  • Online/Offline Installation: Online package (~670MB, requires network to pull images), Offline package (~4.4GB, ready to use out of the box)
  • One-click Deployment: macOS installer automatically detects environment, installs Docker, and deploys services
  • Desktop Application: Supports macOS (Intel and Apple Silicon), Windows version in development
  • Intuitive Interface: Modern UI design with light/dark theme switching

2.5 Privacy and Security ​

IMPORTANT

Data Security Commitment:

  • Local Deployment: By default, all services run locally, data never leaves your machine
  • Distributed Deployment: Optionally deploy Docker services to a private server, desktop client connects securely via SSH
  • Data Encryption: Sensitive information stored with encryption
  • Offline Available: Speech recognition runs locally, optional local LLM models for complete offline operation

3. Use Cases ​

TIP

For detailed use case descriptions, please see the Use Cases page.

3.1 Mock Interview Training ​

  • AI Mock Interviewer: AI automatically asks questions based on job description and resume
  • Answer Evaluation: AI evaluates answer quality, provides scores and improvement suggestions
  • Repeated Practice: Practice weak areas repeatedly until mastered

3.2 Interview Preparation ​

  • Knowledge Base Organization: Upload resume, project documents, and technical notes to build a personal knowledge base
  • Question Bank Preparation: Create and manage personalized interview question banks with preset common questions
  • Voice Testing: Test microphone and speaker to ensure devices work properly

3.3 Skill Improvement ​

  • Language Expression Training: Train structured expression (STAR method) and concise communication skills
  • Stress Response Training: Simulate rapid consecutive questioning to build mental resilience
  • English Interview Preparation: Supports English speech recognition and responses for English interview practice

3.4 Career Advancement ​

  • Promotion Defense Preparation: Systematically organize technical capabilities and project contributions
  • Management Position Preparation: Train team management and business development presentation skills
  • Data-driven Expression: Support defense content with data and case studies

4. Technical Features ​

TIP

For detailed technical architecture, please see the Technical Architecture page.

4.1 Frontend Technology ​

Web Application:

  • React 18.3.1: Modern frontend framework
  • TypeScript 5.5.4: Type safety
  • Ant Design 5.27.3: Enterprise-grade UI component library
  • Vite 5.4.10: Ultra-fast development build tool
  • Tailwind CSS 3.4.14: Atomic CSS framework

Desktop Client:

  • Electron 39.2.2: Cross-platform desktop application framework (built-in Node.js 22.21.1, Chromium 142.0.7444.162, V8 14.2.231.18)
  • React 18.2.0: Frontend framework
  • TypeScript 5.2.2: Type safety
  • Vite 5.2.0: Build tool
  • Native Audio Module: Low-latency audio capture based on Node-API (C++ native extension)
  • System Integration: Global shortcuts, system tray, floating window

4.2 Backend Technology ​

  • Node.js 20.x/22.x: High-performance JavaScript runtime (web/web-api uses 20.x, llm-router/rag-service uses 22.x)
  • pnpm >=9.15.9: Fast, disk-space-efficient package manager
  • Fastify 4.x/5.x: High-performance async web framework
  • SQLite: Lightweight embedded database
  • better-sqlite3 9.6.0: High-performance synchronous SQLite API

4.3 AI Services ​

  • FunASR: Alibaba DAMO Academy open-source speech recognition engine
  • 24+ LLM Support: OpenAI, Claude, Gemini, Zhipu, Qwen, DeepSeek, Kimi, Ollama, etc.
  • ChromaDB 3.1.5: High-performance vector database
  • Piper TTS: Local neural network speech synthesis (supports Chinese and English)
  • AudioTee: System audio capture tool

4.4 Containerized Deployment ​

  • Docker Compose: One-click deployment of all backend services
  • Multi-platform Images: Supports linux/amd64 and linux/arm64
  • Alibaba Cloud Image Registry: High-speed image pulling in China
  • Service Monitoring: Real-time Docker service status monitoring

4.5 Deployment Modes ​

  • Local Mode: Docker services and desktop client both run on local macOS, suitable for personal use
  • Distributed Mode: Docker services deployed to remote server, desktop client runs on macOS, suitable for team sharing or high-performance scenarios
  • SSH Secure Connection: Distributed mode supports password or private key authentication, connection testing ensures correct configuration

5. System Requirements ​

TIP

For detailed system requirements, please see the System Requirements page.

5.1 Hardware Requirements ​

Minimum Configuration:

  • Processor: Intel Core i5 dual-core or Apple Silicon (M1/M2/M3)
  • Memory: 4GB RAM
  • Storage: 10GB available space
  • Display: 1280 x 720 resolution

Recommended Configuration:

  • Processor: Intel Core i7 quad-core or Apple Silicon (M1 Pro/M2 Pro/M3 Pro)
  • Memory: 8GB RAM
  • Storage: 15GB available space
  • Display: 1920 x 1080 resolution or higher

5.2 Software Requirements ​

Operating System:

  • macOS: macOS 13.0 (Ventura) or later (macOS 15+ recommended)
  • Windows: In development, coming soon

Required Software:

  • Docker Desktop 4.0+: Backend service runtime environment

External Services:

  • LLM API: At least one LLM API key (OpenAI, Zhipu, Qwen, etc.)
  • Python 3.9+ (optional): For Piper TTS local speech synthesis

5.3 System Permissions ​

Required Permissions:

  • Microphone Permission: For capturing voice input
  • Screen Recording Permission: For capturing system audio

Optional Permissions:

  • Accessibility Permission: For global shortcuts
  • Full Disk Access Permission: For log file read/write

6. Version Information ​

NOTE

Open Source vs Subscription Version

  • Open Source Version: Includes all core interview training features, suitable for individual users and small teams
  • Subscription Version: Based on the open source version, adds preset question bank features (continuous iteration in the future)

Subscription Plans ​

CueMate provides three flexible subscription plans to meet the needs of different users:

PlanDurationPriceUse Case
Monthly1 month¥59Short-term interview prep, trial experience
Annual1 year¥199Long-term interview training, job hunting season
LifetimeLifetime (100 years)¥399One-time purchase, use forever

TIP

Recommended Choice:

  • If you are preparing for an interview soon, choose Monthly Subscription
  • If you plan to improve your interviewing skills long-term, choose Annual Subscription (equivalent to ¥16.6/month)
  • If you want it once and for all, choose Lifetime License (best value)

Subscription Benefits:

  • All subscription plans include full functionality
  • Free updates to the latest version during the subscription period
  • Exclusive preset question bank (continuously updated)
  • Priority technical support services

How to Purchase:

Released under the GPL-3.0 License.

Copyright © 2025-present CueMate Team