v0.1.3

GPTSpeak v0.1.3: Long Text Support & Progress Tracking

New Features:

• Long Text Handling: Automatically splits and processes texts exceeding the 4096 character limit.
• Progress Visualization: Added tqdm progress bars for better insight into long text processing.

Improvements:

• Enhanced logging for clearer feedback on text-to-speech conversion steps.
• Optimized chunking algorithm for more efficient processing of large texts.

User Experience:

• Seamless handling of texts of any length without user intervention.
• Improved console output for better understanding of the conversion process.

This release significantly enhances GPTSpeak's capability to handle large texts while providing users with clear progress indicators.

v0.1.1

Bug fix: wasn't processing input files correctly.

v0.1.0

This release introduces a simple CLI and Python package for text-to-speech conversion using OpenAI's TTS models.

• CLI commands: gptspeak "text", convert, play, concat, configure
• Python functions: convert_text_to_speech(), convert_text_to_speech_direct(), play_audio()
• Multiple TTS models (tts-1, tts-1-hd) and voices (alloy, echo, fable, onyx, nova, shimmer)
• Easy configuration with gptspeak configure
• Cross-platform compatibility (macOS, Linux, Windows)

Install with pip install gptspeak. Set your OpenAI API key in the environment.

Example: gptspeak "Hello, world!" -o hello.mp3 -m tts-1-hd -v nova

Explore the README for detailed usage instructions and examples.