UTTS

Universal interface to test and compare text-to-speech models. Currently supports:

• OpenAI TTS
• ElevenLabs
• Kokoro
• Orpheus
• Zyphra/Zonos
• Hume AI
• Cartesia

Installation

pip install utts

To install the latest development version, use:

pip install --upgrade git+https://github.com/arch1baald/utts.git

Obtain API keys for the services you want to use:

• OpenAI
• ElevenLabs
• Replicate (for Kokoro and Orpheus)
• Zyphra/Zonos
• Hume AI
• Cartesia

Quick Start

The simplest way to get started is to open the notebook in Colab:

Or test from Jupyter Notebook:

from IPython.display import Audio

import utts

client = utts.UTTSClient(elevenlabs_api_key="your_elevenlabs_api_key")
audio = client.elevenlabs.generate('Hello, world!')
Audio(audio)

For batch generation use utts.utils.batch_generate.

Development

Prerequisites

• Python 3.11.12 or higher
• uv - Modern Python package installer and resolver
• Make - for running development commands

Setup

Clone the repository:

git clone https://github.com/arch1baald/utts.git
cd utts

Install in development mode:

make install-dev

Development Commands

For all available commands:

make help

Run linting and type checking:

make lint