

Pre-Installed Coqui TTS

Get Coqui TTS pre-installed and ready to go from the Database Mart Marketplace—just deploy and use, no setup hassle.

Overview

Coqui TTS is a library for advanced Text-to-Speech generation, offering high-performance deep learning models for TTS and voice conversion tasks. It provides a comprehensive ecosystem—from pretrained models in over 1,100 languages to tools for training new models and fine-tuning existing ones in any language.

Select a pre-installed Coqui 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 Coqui TTS Marketplace image is available for Ubuntu Server 22 LTS 64-bit.

Supported Products / Plans

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

GPU VPS

Professional GPU VPS - RTX A4000
Advanced GPU VPS - RTX 5090

GPU Dedicated Server

Basic Dedicated GPU Server - RTX 5060
Advanced Dedicated GPU Server - RTX 3060 Ti
Advanced Dedicated GPU Server - RTX A5000
Enterprise Dedicated GPU Server - RTX 5090
Enterprise Dedicated GPU Server - RTX 4090

View compatible plans →

Coqui TTS Version

Database Mart provides the v0.22.0 version of Coqui TTS, pre-installed and ready to use.

What's Installed

When you select the Coqui 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 11.8+ pre-installed for GPU acceleration (when applicable)
Python Environment: Python 3.10 with a dedicated virtual environment (uv strongly recommended) for dependency management

Coqui TTS Core Components

Coqui TTS v0.22.0: The advanced text-to-speech library with pretrained models in 1,100+ languages
PyTorch Framework: PyTorch 2.2+ with CUDA support pre-installed
Pre-trained Models: XTTSv2 (voice cloning with 3-second audio clip), multi-speaker models, and Fairseq models for 1,100+ languages

Inference & Deployment Tools

Python API: Full TTS API with support for multi-speaker, multi-lingual synthesis, and voice conversion
CLI Tool: tts command-line interface for direct speech synthesis and model management
Server Components: TTS server with REST API (port 5002) for production deployment
Optional Dependencies: Extras for languages (Japanese, Korean, Chinese, Bengali) and server deployment

Installation Process

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

Deploys the selected Linux operating system (Ubuntu Server 22.04 LTS).
Installs system dependencies, including build-essential, ffmpeg, and other essential libraries.
Creates a Python virtual environment and installs core dependencies:
- PyTorch 2.2+ with CUDA support
- Coqui TTS library (version 0.22.0)
- Server extras for API deployment (coqui-tts[server])
- Language-specific dependencies as needed (Japanese, Chinese, Korean, etc.)
Download and configure the selected pre-trained models:
- XTTSv2 model for voice cloning
- Fairseq models for 1,100+ language support
- Models stored in ~/.local/share/tts/

Everything is fully automated—your Coqui 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 Coqui 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/coqui-tts
source venv/bin/activate

# List available models
tts --list_models

Step 3: Test Basic Text-to-Speech

To test the installation with a simple text-to-speech synthesis:

tts --text "Hello, this is a test of Coqui TTS." \
    --model_name "tts_models/en/ljspeech/tacotron2-DDC" \
    --out_path output.wav

Step 4: Use the Python API

from TTS.api import TTS
import torch

# Get device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Initialize TTS with XTTSv2
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)

# List available speakers
print(tts.speakers)

# TTS to a file with a preset speaker
tts.tts_to_file(
    text="Hello world! This is voice synthesis with Coqui TTS.",
    speaker="Craig Gutsy",  # Preset speaker name
    language="en",
    file_path="output.wav"
)

Step 5: Voice Cloning with XTTSv2

# Clone a voice from a reference audio file
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)

# Generate speech using a reference voice
wav = tts.tts(
    text="This is voice cloning with a 3-second audio sample.",
    speaker_wav="my_reference_audio.wav",  # 3-10 second audio clip
    language="en"
)

# Save to file
tts.tts_to_file(
    text="This is voice cloning with a reference voice.",
    speaker_wav="my_reference_audio.wav",
    language="en",
    file_path="cloned_voice.wav"
)

Step 6: Start the TTS Server

# Start the server
tts-server --model_name "tts_models/multilingual/multi-dataset/xtts_v2" \
    --port 5002 \
    --use_cuda true

Step 7: Use Voice Conversion

# Voice conversion - transform source voice to target voice
tts = TTS("voice_conversion_models/multilingual/vctk/freevc24").to("cuda")
tts.voice_conversion_to_file(
    source_wav="my/source.wav",
    target_wav="my/target.wav",
    file_path="converted_voice.wav"
)

Notes

Use clean, isolated audio samples (3-10 seconds)
Avoid background noise or music in reference audio
Specify the correct language for best results

Frequently Asked Questions

Q: What Coqui TTS models are available from Database Mart?

Database Mart provides pre-installed Coqui TTS with access to all pretrained models, including XTTSv2 (voice cloning, 17 languages), Fairseq models (1,100+ languages), multi-speaker models, and voice conversion models.

Q: What are the hardware requirements for XTTSv2?

XTTSv2 requires:

Minimum: 8GB GPU VRAM, CUDA 11.8+
Recommended: 16GB+ VRAM for optimal performance

Q: What languages does Coqui TTS support?

Coqui TTS supports:

XTTSv2: 17 languages including English, Spanish, French, Japanese, Chinese, and more
Fairseq models: Over 1,100 languages
Additional models available for specific languages

Q: Can I use Coqui TTS for streaming applications?

Yes. XTTSv2 supports streaming inference with less than 200ms latency, making it ideal for real-time voice applications like chatbots and virtual assistants.

Q: Is data secure with a pre-installed server?

Yes. Since Coqui TTS runs on your own provisioned server, all audio data, voice samples, and text inputs stay within your infrastructure. You have full control over network isolation, access control, and data privacy.