Pre-Installed Kokoro TTS

Overview

Kokoro TTS is a family of state-of-the-art, open-weight text-to-speech models designed for high-quality speech synthesis and voice blending. It includes the lightweight 82M-parameter Kokoro-82M model, which delivers comparable quality to larger models while being significantly faster and more cost-efficient. Kokoro supports multiple languages including American English, British English, French, Italian, Japanese, and Mandarin Chinese, with over 50 voices across 8 languages. It features voice blending with customizable weights, EPUB and PDF document support, adjustable speech speed, real-time streaming audio playback, and multiple output formats (WAV and MP3).

Select a pre-installed Kokoro TTS Marketplace image and get a fully configured server that's ready to use immediately—no manual installation or complex setup required.

Supported Operating Systems

The Kokoro TTS Marketplace image is available for Ubuntu Server 22 LTS 64-bit.

Supported Products / Plans

The Kokoro TTS Marketplace image is currently available across the following plans:

• Basic Dedicated GPU Server - T1000
• Basic Dedicated GPU Server - GTX 1650
• Basic Dedicated GPU Server - GTX 1660
• Basic Dedicated GPU Server - RTX 4060
• Basic Dedicated GPU Server - RTX 5060
• Advanced Dedicated GPU Server - RTX 3060 Ti
• Advanced Dedicated GPU Server - RTX 2060
• Professional Dedicated GPU Server - RTX 2060

View compatible plans →

Kokoro TTS Version

Database Mart provides the v0.1.3 version of Kokoro TTS, pre-installed and ready to use.

What's Installed

When you select the Kokoro TTS Marketplace image, Database Mart automatically installs and configures:
Core Operating Environment

• Operating System: Ubuntu Server 22.04 LTS, pre-optimized for TTS workloads
• GPU Drivers & Acceleration: NVIDIA drivers and CUDA pre-installed for GPU acceleration (when applicable)
• Python Environment: Python 3.10+ with a dedicated virtual environment for dependency management

Kokoro TTS Core Components

• Kokoro-82M Model: Pre-trained model weights (approximately 320MB) downloaded automatically
• Voice Configuration Files: voices.json and voice data files containing 54+ preset voices across multiple languages
• Inference Engine: Pre-configured with kokoro-tts CLI tool or FastAPI-based REST API server

Installation Process

During server provisioning, Database Mart automatically performs the following steps:

1. Deploys the selected Linux operating system (Ubuntu Server 22.04 LTS).

2. Installs system dependencies, including espeak-ng, libsndfile1, ffmpeg, and other audio processing tools.

3. Creates a Python virtual environment and installs core dependencies:

   • PyTorch or ONNX Runtime (GPU support when available)
   • FastAPI and Uvicorn for REST API serving
   • kokoro-tts CLI tool
   • Audio processing libraries (librosa, soundfile, scipy)

4. Downloads and configures the Kokoro-82M model weights and voice configuration files.

5. Configures the audio output format (WAV default, MP3 optional) and sample rate (24kHz default).

Everything is fully automated—your Kokoro TTS server is ready to use as soon as deployment is complete.

Getting Started After Deployment

After your server has been provisioned, follow these steps to begin using Kokoro TTS.

Step 1: Access the Server

Once deployment is complete, connect to your server via SSH using the credentials provided by Database Mart:

ssh administrator@your-server-ip

Step 2: Activate the Environment and Verify Installation

# Activate the pre-configured virtual environment
cd /opt/kokoro
source venv/bin/activate

# Verify the installation
kokoro-tts --help

Expected output: Help menu showing available commands and options.

Step 3: Test Basic Text-to-Speech

To test the installation with a simple text file:

# Create a test text file
echo "Hello, this is a test of Kokoro TTS." > test.txt

# Generate speech
kokoro-tts test.txt output.wav --voice af_sarah

This generates output.wav using the American female voice "af_sarah".

Step 4: Start the REST API Server

The server comes with a pre-configured FastAPI server. Start it using:

# Start the API server
cd /opt/kokoro/api
python main.py

The API server will start and be accessible at http://your-server-ip:8000, with interactive API documentation at http://your-server-ip:8000/docs.

Step 5: Test the API with a Simple Request

Once the API server is running, you can test it using curl:

curl -X POST "http://localhost:8000/synthesize" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, this is a test of the Kokoro API.", "voice": "af_sarah"}' \
  --output speech.wav

Step 6: Process an EPUB Book or PDF Document

Kokoro TTS supports EPUB and PDF input for audiobook creation:

# Process an EPUB file and split into chapters
kokoro-tts book.epub --split-output ./chapters/ --format mp3 --voice bf_emma

This creates MP3 files for each chapter in the chapters directory.

Step 7: Use Voice Blending

Kokoro supports blending two voices with custom weights:

# 60% Sarah, 40% Adam
kokoro-tts test.txt output.wav --voice "af_sarah:60,am_adam:40"

Step 8: Stream Audio Directly

For real-time playback, use the --stream option:

kokoro-tts test.txt --stream --speed 0.8

Notes

Audio Format
Kokoro outputs audio at a 24kHz sample rate with 16-bit depth, delivering high-quality, natural-sounding speech.

Multi-Language Support
8 languages with 54 preset voices

Voice Blending
Blend voices with custom weights using the "voice1:weight,voice2:weight" format

Frequently Asked Questions

Q: What are the hardware requirements?

Kokoro-82M is designed to be lightweight and efficient. It can run on CPU-only systems (4 cores, 8GB RAM minimum) or with GPU acceleration for lower latency. The model weights require approximately 320MB of disk space.

Q: What file formats are supported as input?

Kokoro supports TXT, EPUB, and PDF file formats for text input, making it ideal for audiobook creation and document processing.

Q: What audio formats are supported for output?

Kokoro supports WAV (default, high-quality) and MP3 (compressed) audio formats.