Kitten TTS API Guide

Getting Started

from kittentts import KittenTTS
model = KittenTTS("KittenML/kitten-tts-mini-0.8")

Core Methods

• generate(text, voice, speed): Returns numpy audio array
• generate_to_file(text, path, voice, speed): Saves WAV file
• available_voices: List of all voice names
• normalize_text(text): Clean and normalize input text

Batch Processing

scripts = {
    "intro": "Welcome to the show!",
    "main": "Today we discuss the latest tech news.",
    "outro": "Thanks for listening!"
}
for name, text in scripts.items():
    model.generate_to_file(text, name + ".wav", voice="Jasper")

Error Handling

try:
    model.generate_to_file("Test", "out.wav", voice="InvalidVoice")
except ValueError as e:
    print("Voice not found:", e)