SecondVoice

Real-time Chinese to French translation system for live meetings.

Overview

SecondVoice captures audio, transcribes Chinese speech using OpenAI's Whisper API, and translates it to French using Claude AI in real-time. Perfect for understanding Chinese meetings on the fly.

Features

• 🎤 Real-time audio capture
• 🗣️ Chinese speech-to-text (Whisper API)
• 🌐 Chinese to French translation (Claude API)
• 🖥️ Clean ImGui interface
• 💾 Full recording saved to disk
• ⚙️ Configurable chunk sizes and settings

Requirements

System Dependencies (Linux)

# PortAudio
sudo apt install libasound2-dev

# OpenGL
sudo apt install libgl1-mesa-dev libglu1-mesa-dev

vcpkg

Install vcpkg if not already installed:

git clone https://github.com/microsoft/vcpkg.git
cd vcpkg
./bootstrap-vcpkg.sh
export VCPKG_ROOT=$(pwd)

Setup

1. Clone the repository

git clone <repository-url>
cd secondvoice

2. Create .env file (copy from .env.example)

cp .env.example .env
# Edit .env and add your API keys:
# OPENAI_API_KEY=sk-...
# ANTHROPIC_API_KEY=sk-ant-...

3. Configure settings (optional)

Edit config.json to customize:

• Audio chunk duration (default: 10s)
• Sample rate (default: 16kHz)
• UI window size
• Output directory

4. Build the project

# Configure with vcpkg
cmake -B build -DCMAKE_TOOLCHAIN_FILE=$VCPKG_ROOT/scripts/buildsystems/vcpkg.cmake

# Build
cmake --build build -j$(nproc)

Usage

cd build
./SecondVoice

The application will:

1. Open an ImGui window
2. Start capturing audio from your microphone
3. Display Chinese transcriptions and French translations in real-time
4. Click STOP RECORDING button to finish
5. Save the full audio recording to recordings/recording_YYYYMMDD_HHMMSS.wav

Architecture

Audio Capture (PortAudio)
    ↓
Whisper API (Speech-to-Text)
    ↓
Claude API (Translation)
    ↓
ImGui UI (Display)

Threading Model

• Thread 1: Audio capture (PortAudio callback)
• Thread 2: AI processing (Whisper + Claude API calls)
• Thread 3: UI rendering (ImGui + OpenGL)

Configuration

config.json

{
  "audio": {
    "sample_rate": 16000,
    "channels": 1,
    "chunk_duration_seconds": 10
  },
  "whisper": {
    "model": "whisper-1",
    "language": "zh"
  },
  "claude": {
    "model": "claude-haiku-4-20250514",
    "max_tokens": 1024
  }
}

.env

OPENAI_API_KEY=sk-...
ANTHROPIC_API_KEY=sk-ant-...

Cost Estimation

• Whisper: ~$0.006/minute (~$0.36/hour)
• Claude Haiku: ~$0.03-0.05/hour
• Total: ~$0.40/hour of recording

Project Structure

secondvoice/
├── src/
│   ├── main.cpp                 # Entry point
│   ├── audio/                   # Audio capture & buffer
│   ├── api/                     # Whisper & Claude clients
│   ├── ui/                      # ImGui interface
│   ├── utils/                   # Config & thread-safe queue
│   └── core/                    # Pipeline orchestration
├── docs/                        # Documentation
├── recordings/                  # Output recordings
├── config.json                  # Runtime configuration
├── .env                         # API keys (not committed)
└── CMakeLists.txt              # Build configuration

Development

Building in Debug Mode

cmake -B build -DCMAKE_BUILD_TYPE=Debug -DCMAKE_TOOLCHAIN_FILE=$VCPKG_ROOT/scripts/buildsystems/vcpkg.cmake
cmake --build build

Running Tests

# TODO: Add tests

Troubleshooting

No audio capture

• Check microphone permissions
• Verify PortAudio is properly installed: pa_devs (if available)
• Try different audio device in code

API errors

• Verify API keys in .env are correct
• Check internet connection
• Monitor API rate limits

Build errors

• Ensure vcpkg is properly set up
• Check all system dependencies are installed
• Try cmake --build build --clean-first

Roadmap

Phase 1 - MVP (Current)

• ✅ Audio capture
• ✅ Whisper integration
• ✅ Claude integration
• ✅ ImGui UI
• ✅ Stop button

Phase 2 - Enhancement

• ⬜ Auto-summary post-meeting
• ⬜ Export transcripts
• ⬜ Search functionality
• ⬜ Speaker diarization
• ⬜ Replay mode

License

See LICENSE file.

Contributing

This is a personal project, but suggestions and bug reports are welcome via issues.

Contact

See docs/SecondVoice.md for project context and motivation.