Backed by Combinator

Voice AI
Made in Europe

Natural voices in 26+ languages, developed and hosted in Europe, fully GDPR compliant.

Get StartedView Pricing

Good afternoon, your appointment is on 03/15/2025 at 2:30 p.m. The office is located at 42a Bridge Street. For questions, reach us at 02079460123 or info@clinic.co.uk.

Real model output · first audio in <50 ms

Voices

Voices that sound human

Real recorded voices, ready to stream or clone your own.

Noah
Conversational

Noah

Quick and clear. Cuts straight to the point.

Olivia
Conversational

Olivia

Composed and warm. Stays calm under pressure.

Gustav
Story

Gustav

Deep and steady. Quiet authority you trust.

Samantha
Conversational

Samantha

Bright and helpful. Always ready to assist.

Nick
Conversational

Nick

Easygoing and clear. Makes complex things simple.

Your voiceClone it in under a minute.

Start free — no credit card required.

Get startedLog in

Edge Cases

Trained on real-world edge cases

Street names, postal codes, phone numbers, and email addresses are no longer a problem.

Real model outputkugel-3

Long numbers, read just right.

Your transfer to IBAN GB29NWBK60161331926819 is confirmed. Reference 7703248159.

Digit-perfect IBANs, phone numbers, and policy IDs.

Try your use cases

Numbers, dates, addresses and currencies, pronounced correctly, every time.

Get startedLog in

Languages

Speak your customers’ language

26 languages, native pronunciation, accents & dialects.

Map showing supported languagesEnglishGermanFrenchSpanishItalianPortugueseDutchPolishCzechSlovakHungarianRomanianBulgarianUkrainianSwedishDanishNorwegianFinnishCroatianSlovenianSerbianGreekTurkishArabicAmerican EnglishLatin American SpanishBrazilian PortugueseCanadian French
  • English
  • German
  • French
  • Spanish
  • Italian
  • Portuguese
  • Dutch

By the numbers

Production voice AI, in figures

<0ms

time to first audio

0

languages, native voices

<0min

to clone any voice

0%

built & hosted in the EU

Ready to put these numbers to work?

Real-time, EU-hosted voice that scales with your product.

Get startedLog in

Developers

Three lines to production

Drop-in for Pipecat, LiveKit, or any pipeline you already run.

from kugelaudio import KugelAudio
client = KugelAudio(api_key="sk-...")
client.connect()  # prewarm the connection
audio = client.tts.generate(
    text="Good afternoon, this is Lena from Kugel.",
    model_id="kugel-3",
    voice_id=1072,
)
audio.save("output.wav")
PipecatLiveKit

Data Sovereignty

Your data stays in Europe

Built, trained and hosted in the EU — outside the reach of the US Cloud Act.

On-Premise

Same SDK, your infra

EU Servers

Hosted in Europe

GDPR

Compliant

No US Cloud Act

EU jurisdiction only

Need on-premise or dedicated capacity?

Talk to our team about Enterprise plans and EU hosting.

Get started

Pricing

Text-to-speech API rates

Priced per generated audio minute.

Enterprise

On-premise & dedicated deployment

  • Higher custom concurrency limits
  • On-premise hosting
  • EU data residency
  • 24/7 support
  • Dedicated account manager
  • Lower rates with committed usage

kugel-2-turbo

Fast, budget-friendly text-to-speech model

€0.0375/ min

  • ~40–50 ms TTFA*
  • ~€26.79 / 1M text tokens**
  • Integrated normalizer
  • Voice cloning
  • Speed control
  • Break tokens
  • Word-level timestamps
  • Dictionaries
Get API access

kugel-3

Premium text-to-speech model with maximum naturalness

€0.075/ min

  • ~60–80 ms TTFA*
  • ~€53.57 / 1M text tokens**
  • Integrated normalizer
  • Voice cloning
  • Speed control
  • Break tokens
  • Word-level timestamps
  • Dictionaries
  • IPA notations
Get API access

* Inference TTFA, measured server-side. More in the latency docs

** Token costs use an approximate 1,400 tokens-per-minute conversion.