Skip to content

QUICKSTART.md

Latest commit

 

History

History
199 lines (146 loc) · 3.26 KB

QUICKSTART.md

File metadata and controls

199 lines (146 loc) · 3.26 KB

🚀 Kitten TTS - Quick Start Guide

Get up and running in 5 minutes!

Option 1: Docker (Fastest) ⚡

# Clone or download the project
cd kitten-tts

# Start with Docker Compose
docker-compose up -d

# Access WebUI
open http://localhost:8000

That's it! 🎉

Option 2: Python (No Docker) 🐍

# Install dependencies
pip install -r requirements.txt

# Install KittenTTS
pip install https://github.com/KittenML/KittenTTS/releases/download/0.8/kittentts-0.8.0-py3-none-any.whl

# Run server
python app.py

# Access WebUI
open http://localhost:8000

📖 Basic Usage

Web Interface

  1. Open http://localhost:8000
  2. Enter your text
  3. Select a voice
  4. Click "Generate Speech"
  5. Listen or download!

API (cURL)

# Generate speech
curl http://localhost:8000/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kitten-tts-mini-0.8",
    "input": "Hello world!",
    "voice": "Jasper",
    "response_format": "mp3"
  }' \
  --output hello.mp3

# Play it
afplay hello.mp3  # macOS
xdg-open hello.mp3  # Linux
start hello.mp3  # Windows

API (Python)

import requests

response = requests.post(
    "http://localhost:8000/v1/audio/speech",
    json={
        "model": "kitten-tts-mini-0.8",
        "input": "Hello world!",
        "voice": "Jasper",
        "response_format": "mp3"
    }
)

with open("hello.mp3", "wb") as f:
    f.write(response.content)

API (JavaScript)

const response = await fetch('http://localhost:8000/v1/audio/speech', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model: 'kitten-tts-mini-0.8',
    input: 'Hello world!',
    voice: 'Jasper',
    response_format: 'mp3'
  })
});

const blob = await response.blob();
const audio = new Audio(URL.createObjectURL(blob));
audio.play();

🎙️ Available Voices

Voice Description
Bella Female, warm
Jasper Male, clear
Luna Female, soft
Bruno Male, deep
Rosie Female, friendly
Hugo Male, professional
Kiki Female, energetic
Leo Male, casual

🔒 Enable API Key (Optional)

# Create .env file
echo "API_KEY=your-secret-key" > .env

# Restart with authentication
docker-compose down
docker-compose -f docker-compose.api-key.yml up -d

# Use API key in requests
curl http://localhost:8000/v1/audio/speech \
  -H "Authorization: Bearer your-secret-key" \
  ...

🛑 Stop Server

# Docker
docker-compose down

# Python
# Press Ctrl+C

📊 Check Status

# Health check
curl http://localhost:8000/health

# View logs
docker-compose logs -f

🎯 Next Steps

❓ Troubleshooting

Server won't start?

docker-compose logs

Model download fails?

  • Check internet connection
  • First run downloads ~79MB model

Port already in use?

# Change port in .env
PORT=8001

Need help?

Enjoy! 🐱🎵