API Documentation

Learn how to integrate OuteTTS into your applications

Quick Start

Installation

pip install outeai

Python SDK

Basic Usage

from outeai.api.v1 import TTSClient

client = TTSClient(token="...")
audio = client.generate(
    text="this is text to speech model speaking",
    model_id="outetts-0.3-500m",
    temperature=0.1,
    repeat_penalty=1.1,
    speaker="en_male_1"
)

# Files will be saves as wav
audio.save("output.wav")

Parameters

text

The text content to convert to speech

Type: string, Required

model_id

ID of the model to use for generation

Type: string, Required

temperature

Controls randomness in generation. Higher values make output more random

Type: float, Default: 0.1

repeat_penalty

Penalty for repetition in generated speech

Type: float, Default: 1.1

speaker

Speaker ID to use for voice generation

Type: string, Default: "en_male_1"