Kitten TTS v0.8.1: All voices are built-in, no additional downloads needed. Just pick a voice name and start generating.
All 8 Voices Overview
| Voice | Gender | Tone | Best For |
|---|---|---|---|
| Bella | Female | Warm, natural | Narration, audiobooks, podcast intros |
| Jasper | Male | Clear, friendly | YouTube voiceovers, tutorials |
| Luna | Female | Soft, gentle | Meditation, bedtime stories, ASMR |
| Bruno | Male | Deep, authoritative | Documentaries, corporate narration |
| Rosie | Female | Bright, upbeat | Marketing, commercials, social media |
| Hugo | Male | Warm, engaging | Podcasts, conversational content |
| Kiki | Female | Energetic, youthful | TikTok, Shorts, gaming content |
| Leo | Male | Bold, confident | Trailers, promos, dramatic content |
Get Available Voices
from kittentts import KittenTTS
model = KittenTTS("KittenML/kitten-tts-mini-0.8")
print(model.available_voices)
# ['Bella', 'Jasper', 'Luna', 'Bruno', 'Rosie', 'Hugo', 'Kiki', 'Leo']Using a Specific Voice
audio = model.generate("Your text here", voice="Bella")
# Or to file:
model.generate_to_file("Hello world", "output.wav", voice="Jasper")Speed Control
Each voice supports speed adjustment from 0.5x to 2.0x:
# Slower (more dramatic)
model.generate_to_file("Slow speech", "slow.wav", voice="Bruno", speed=0.7)
# Faster (for shorts/reels)
model.generate_to_file("Fast speech", "fast.wav", voice="Kiki", speed=1.5)Voice Selection Guide
For YouTube Videos
Jasper Bella Bruno
Clear, professional narration for tutorials and explainers.
For Podcasts
Hugo Rosie Bella
Warm, conversational tones for long-form audio.
For Shorts / TikTok
Kiki Rosie Leo
Energetic, attention-grabbing styles.
For Audiobooks
Bella Bruno Luna
Smooth, expressive narration for long texts.
Batch Generate All Voices
for voice in model.available_voices:
model.generate_to_file(
"Hi, I am " + voice + ". Welcome to Kitten TTS.",
voice + "_intro.wav",
voice=voice
)