Skip to main content
KugelAudio Hero

​
What is KugelAudio?

KugelAudio is a state-of-the-art text-to-speech (TTS) platform designed for real-time applications. Whether you’re building voice agents, interactive applications, or content creation tools, KugelAudio provides the speed and quality you need.

Quick Start

Get up and running with KugelAudio in under 5 minutes

Generate Speech

Generate high-quality audio from text

Streaming

Real-time audio streaming for low latency

Voices

Browse voices and create custom clones

​
Key Features

kugel-3 is the canonical production model for natural prosody, clean brand voices, multilingual TTS, streaming, and break tags.
Legacy IDs such as kugel-2.5 and kugel-2-turbo remain accepted for backwards compatibility. Use kugel-3 for new integrations.
Stream audio chunks as they’re generated for the lowest possible latency. Perfect for LLM integrations where text arrives token by token.
Create custom voices from audio samples. Clone any voice with just a few seconds of reference audio.
Multilingual single model — 39 languages including DE, EN, FR, ES, IT, NL, PT, PL, RU, ZH, JA, KO, AR. See the TTS endpoint reference for the full list.

​
Available Models

Use kugel-3 for new integrations. See Models for the current model reference.
ModelBest for
kugel-3Voice agents, narration, brand voices, streaming, multilingual TTS, and break tags

​
Getting Started

1

Get Your API Key

Sign up at kugelaudio.com and get your API key from the dashboard.
2

Install the SDK

Choose your preferred SDK and install it:
pip install kugelaudio
3

Generate Your First Audio

from kugelaudio import KugelAudio

client = KugelAudio(api_key="your_api_key")
client.connect()  # Pre-connect at startup (one-time handshake cost)

audio = client.tts.generate(
    text="Hello, world!",
    model_id="kugel-3",
)
audio.save("output.wav")

​
Need Help?

API Reference

Detailed API documentation with examples