Voice AI
Made in Europe
Natural voices in 26 languages, developed and hosted in Europe, fully GDPR compliant.
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
Quick and clear. Cuts straight to the point.
Olivia
Composed and warm. Stays calm under pressure.
Gustav
Deep and steady. Quiet authority you trust.
Samantha
Bright and helpful. Always ready to assist.
Nick
Easygoing and clear. Makes complex things simple.
Start free — no credit card required.
Edge Cases
Trained on real-world edge cases
Street names, postal codes, phone numbers, and email addresses are no longer a problem.
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.
Languages
Speak your customers’ language
26 languages, native pronunciation, accents & dialects.
- English
- German
- French
- Spanish
- Italian
- Portuguese
- Dutch
By the numbers
Fastest time to first audio
Median time to first audio across the leading streaming voice models.
Measured over WebSocket streaming · network round-trip included, connection setup excluded · lower is better
Ready to put these numbers to work?
Real-time, EU-hosted voice that scales with your product.
Developers
Three lines to production
Drop-in for Pipecat, LiveKit, or any pipeline you already run.
from kugelaudio import KugelAudioclient = KugelAudio(api_key="sk-...")client.connect() # prewarm the connectionaudio = client.tts.generate(text="Good afternoon, this is Lena from Kugel.",model_id="kugel-3",voice_id=1072,language="en",)audio.save("output.wav")
Data Sovereignty
Your data stays in Europe
Built, trained and hosted in the EU.
EU Servers
Hosted in Europe
GDPR
Compliant
No training
Never on your content
Sovereign Cloud
Hosting by EU companies only. AWS, Google Cloud, Microsoft Azure and Lambda are not engaged under the Sovereign Cloud agreement at all. No provider with a US parent processes your audio, text or voice references, so no US CLOUD Act order can reach them.
On-Premise
Maximum security on your own hardware. The models run in your data centre, behind your firewall, so audio, text and voice references never leave your infrastructure.
Same SDK and API as the hosted service, so integrations do not change.
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
- Sovereign Cloud (EU-only subprocessors)
- 24/7 support
- Dedicated account manager
- Lower rates with committed usage
kugel-2-turbo
Fast, budget-friendly text-to-speech model
€0.035/ min
- ~40–50 ms TTFA*
- ~€42.42 / 1M characters**
- Integrated normalizer
- Voice cloning
- Speed control
- Break tokens
- Word-level timestamps
- Dictionaries
kugel-3
Premium text-to-speech model with maximum naturalness
€0.07/ min
- ~60–80 ms TTFA*
- ~€84.85 / 1M characters**
- Integrated normalizer
- Voice cloning
- Speed control
- Break tokens
- Word-level timestamps
- Dictionaries
- IPA notations
* Inference TTFA, measured server-side. More in the latency docs
** Character costs assume approximately 825 characters per minute.