contaigents/CHANGELOG.md

Modular AI Content Ecosystem with Audio Generation

# Changelog

All notable changes to the Contaigents CLI will be documented in this file.

## [0.1.0-alpha.6] - 2025-06-17

### Added
- **Audio Generation Command**: New `contaigents audio` command for text-to-speech conversion
  - Support for direct text input (`--text`) and file input (`--file`)
  - Multiple voice options: Zephyr, Breeze, Ember, Tide, Nova, Aurora
  - Configurable output paths and directories
  - Google Gemini TTS integration
  - Automatic audio format detection and WAV header creation
  - Environment variable support for API keys (`GEMINI_API_KEY`)
  - Comprehensive error handling and user feedback
  - File URL output for easy access to generated audio

### Dependencies
- Added `@google/generative-ai` for Gemini TTS integration
- Updated `dotenv` for environment variable management

### Documentation
- Added `AUDIO_COMMAND.md` with comprehensive usage examples
- Updated package description to reflect audio generation capabilities

## [0.1.0-alpha.5] - Previous Release

### Features
- Development server with file editing capabilities
- Web interface for content management
- Local markdown project integration
- Multi-LLM support (OpenAI, Anthropic, Google, etc.)

---

## Usage Examples for Audio Command

```bash
# Generate from text
contaigents audio --text "Hello, this is a test"

# Generate from file
contaigents audio --file script.txt --output my_audio

# Use different voice
contaigents audio --text "Hello world" --voice Breeze

# Custom output directory
contaigents audio --text "Hello world" --output-dir ./audio_files
```