utts 0.1.0

Universal interface to test and compare text-to-speech providers

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

or install from source:

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:

import os
from IPython.display import Audio
import utts.openai

os.environ["OPENAI__API_KEY"] = "<openai-api-key>"
audio = utts.openai.generate('Hello, world!', 'echo')
Audio(audio)

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