Best voices for tutorials: Jasper (clear, friendly male) and Bella (warm, natural female). Use speed=1.0 for optimal comprehension.

Why Kitten TTS for Tutorials?

  • Crystal-clear pronunciation for technical terms
  • Consistent voice across an entire tutorial series
  • No microphone, no recording setup, no retakes
  • Free -- produce unlimited tutorial content

Step-by-Step Tutorial Script

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

# Tutorial structure
steps = [
    (1, "Welcome to this tutorial. Today we will learn how to set up a Python virtual environment.", "intro"),
    (2, "Step one: Open your terminal and navigate to your project folder.", "step1"),
    (3, "Step two: Run python -m venv venv to create the environment.", "step2"),
    (4, "Step three: Activate it with source venv/bin/activate.", "step3"),
    (5, "Step four: Install packages with pip install.", "step4"),
    (6, "That is it! You now have an isolated Python environment.", "outro"),
]

for num, text, filename in steps:
    model.generate_to_file(text, filename + ".wav", voice="Jasper", speed=0.95)
    print("Step %d done" % num)

Tutorial Voice Tips

ContentVoiceSpeed
Programming / TechJasper0.95 (slightly slower for clarity)
Design / CreativeBella1.0 (natural)
Business / FinanceBruno0.95 (authoritative)
DIY / CraftsRosie1.05 (friendly, approachable)

Best Practices

  • Number your steps: Helps viewers follow along
  • Pause between steps: Leave 1-2 second gaps for viewers to process
  • Repeat key commands: Say important commands twice for emphasis
  • Consistent branding: Use same intro/outro voice across your series