• fix(ci): simplify changelog generation in GitHub Actions workflow
• fix(ci): update changelog generation in GitHub Actions workflow
• fix(ci): add GitHub workflow permissions for release creation
• fix(ci): add CI=false to Electron build steps in GitHub Actions
• fix(ci): prevent treating ESLint warnings as errors in GitHub Actions
• ci(github): add GitHub Actions workflows for automated builds and releases
• ci(github): add GitHub Actions workflows for automated builds and releases
• Update README.md
• Update README.md
• Update README.md
• Update README.md
• docs(readme): add demo video section
• Update README.md
• docs(readme): improve documentation with detailed audio routing explanation
• docs(readme): rewrite README in English with modern format
• docs(legal): add GNU Affero General Public License v3.0
• style(ui): update application title from Realtime to Sokuji
• feat(audio): add Space key shortcut for push-to-talk
• refactor(ui): move OpenAI API key setting to top of settings panel
• style(ui): match Input/Output label font size with button text
• style(ui): improve audio visualization and controls layout
• feat(settings): update default system instructions for Chinese to Japanese translation
• refactor(audio): disable interrupt handler and remove debug log
• refactor(ui): remove debug logs and fix error handling
• feat(ui): implement auto-scrolling for conversation container
• fix(api): update OpenAI Realtime API connection to use model from settings
• refactor(audio): create dedicated AudioContext for device management
• fix(settings): correct VoiceOption usage in settings panel
• feat(audio): implement audio visualization and realtime client integration
• refactor(ui): move header from MainPanel to MainLayout
• feat(logs): add auto-scroll functionality to logs panel
• fix(ui): swap client and server arrow icons in logs panel
• feat(logs): implement OpenAI Realtime API event display in LogsPanel
• feat(session): implement new conversation session management
• refactor: remove TokenGenerator and generate-token functionality
• feat(audio): add wavtools library for audio processing
• feat(settings): expand token generation options and unify settings management
• refactor: optimize audio device handling and remove redundant console logs
• refactor: improve audio device selection logic and maintain device persistence
• feat(audio): add toggling functionality for virtual speaker connections
• feat(audio-panel): add warning for virtual speaker selection
• refactor(audio): improve device selection and initialization logic
• feat(audio): improve virtual speaker connection management
• feat: prioritize Sokuji_Virtual_Speaker as default audio output device
• fix: restore loading of model setting during initialization
• refactor: simplify audio output device handling and improve session management
• refactor: simplify and modularize audio port connection logic
• docs: update README with instructions for API key setup, app build, and installation
• docs(readme): update with latest features and implementation details - Add API key validation and token generation features - Include configuration persistence information - Add virtual microphone visual indicators and warnings - Update audio handling features (multi-channel support, device cleanup) - Document orphaned device cleanup on application startup - Add TOML to technologies list for configuration storage - Include details about log panel token usage display
• feat(api): add API key validation and improve token handling
• feat(config): add OpenAI token generation and persistent configuration
• feat(audio): add virtual microphone warning and fix hot reload
• docs: update README with virtual audio device functionality and packaging details
• fix(electron): resolve resource loading issues in packaged application
• feat(audio): implement automatic connection between virtual audio devices
• feat(app): set application name to 'sokuji' in PulseAudio
• refactor(audio): remove output device waveform visualization
• feat(audio): add test MP3 playback with session controls
• feat(audio): improve device management and add output visualization
• style(ui): improve audio device icons for better visual clarity
• refactor(audio): optimize audio visualization and device handling
• feat(audio): add output device support and refresh functionality
• Replace PipeWire with PulseAudio for virtual audio devices
• feat(settings): restructure settings panel layout and enhance styling for better usability
• feat(audio): add audio device selection and visualization to the main layout
• feat(layout): enhance log and settings panel toggling with improved button styles
• feat(pipewire): implement PipeWire loopback functionality and IPC handlers
• feat(main-panel): enhance audio device selection, waveform visualization, and UI
• docs: update README with accurate project information and features
• first commit
• Initialize project using Create React App