New

Unparalleled Voice Cloning Quality

Create a high-quality voice clone from a real human voice and use it in all your business and commercial applications.

Create personalized listening experiences at scale with custom AI voices

Play Icon
Elon
Audio Bars
elon
Play Icon
Kevin
Audio Bars
kevin
Play Icon
JFK
Audio Bars
jfk
Play Icon
Gary
Audio Bars
gary
Play Icon
Tom
Audio Bars
tom
Play Icon
Offerman
Audio Bars
offerman
Play Icon
Rogan
Audio Bars
rogan

Book a free consultation call

Trusted by 7000+ users and teams of all sizes

brands
brands
brands
brands
brands
brands

Peregrine ™ A Generative Text to Speech Model by Play.ht

Unlike most standard speech synthesis machine learning models and Text to Speech APIs that are designed to trade quality and expressiveness for computing performance, we designed Peregrine from the ground up to generate the most expressive speech and imitate a human voice vividly.

Peregrine employs the same concept as large language models such as Dalle and GPT-2.

As a result, the ultra-realistic voices generated by Peregrine pick up the intricacies of human speech like no other. Be it emotion, tone, or even laughter! All in a self-supervised manner.

Play Icon
William US
Audio Bars
us
Play Icon
Lottie UK
Audio Bars
uk
Play Icon
Stella UK
Audio Bars
uk
Play Icon
Anthony US
Audio Bars
us
Play Icon
Evelyn US
Audio Bars
us
Play Icon
Frederick UK
Audio Bars
uk
Play Icon
Arthur UK
Audio Bars
uk
Play Icon
Susan US
Audio Bars
us

How it works

    1
  • We conduct a discovery call with you to understand your requirements and evaluate your use case.
  • 2
  • Acquire voice recordings of the voice talent.
  • 3
  • Train the model on the voice.
  • 4
  • Onboard you and your team on our platform with a kick-off session so you can start creating audio.
How it works

Our Ethics

Our ethic
  • We do not tolerate content that is created for unlawful, hateful, obscene, pornography, or intends to impersonate another person.
  • None of the voices are ever cloned without the written consent of the individual who's voice is being cloned. In some cases, we have cloned a few celebrity voices including Joe Rogan, Steve Jobs, and Elon Musk. However, these voices are not available for public use. The reason behind cloning these voices was solely to showcase the capability of our technology and how natural the voices can be.
  • Our voice cloning technology is not available through a public API. This is a manual process wherein we handle each request individually and allocate time and resources to ensure the voice being cloned is not used for any unethical purposes.
  • We ensure written consents and contractual agreements of the voice owners are in place for every project we take on.
  • We work with clients who share the same pricinciples and values as ourlselves.
  • We plan to improve our technology in a way that allows us to easily differentiate between a real human voice and that which is created using Play.ht.

Frequently Asked Questions

Yes, you can either provide us with the voice talent, or we can find one for you.

We evaluate voice cloning requests on a case-by-case basis. Please get in touch with us to help us understand your requirements and share a quote with you.

Once we have your requirements and the legal documentation in place, it might take about a week to train the model on the voice.
Although our model is powerful enough to clone a voice with an audio recording as small as 30 seconds, we prefer to use studio-quality audio at least an hour in length.

Start creating a custom voice for your brand today