Text-to-Speech Pipeline with Kokoro TTS

A Python script that converts text into natural-sounding speech using the Kokoro TTS engine. The script processes a transcript file, generates speech segments, and merges them into a single audio file.

Features:

• Reads text from a transcript file
• Generates speech segments with customizable voice and speed settings
• Saves individual audio segments and their corresponding text
• Merges all audio segments into a single WAV file using FFmpeg
• Organizes output in timestamped directories