Uberduck AI is the first open source voice AI platform that enables developers to use thousands of real human voices from over 20,000 speakers to create smart personal assistants. Create a personalized assistant that interacts with your customers. It’s that easy. Read More
Get a voice that sounds human, but unlike any human voice you’ve heard before. Voice assistants like Alexa, Cortana, Siri, Google Assistant and now Cortana on Windows, are already a part of our lives, but they are too limited in their capabilities. Voice is the next big thing, and Uberduck offers the only open-source platform for creating intelligent personal assistants. Uberduck combines speech synthesis and natural language understanding to give you a smart virtual assistant that understands your voice, responds appropriately and doesn’t fall flat when you get emotional. We will be able to create any voice we want, and if we so desire, we will be able to add features that Amazon, Apple, Microsoft and Google can only dream of.
Uberduck
UberDuck is the first open source voice AI platform that enables developers to use thousands of real human voices from over 20,000 speakers to create smart personal assistants. Learn More
It Create a personalized assistant that interacts with your customers. It’s that easy.
Uberduck combines speech synthesis and natural language understanding to give you a smart virtual assistant that understands your voice, responds appropriately and doesn’t fall flat when you get emotional.
We will be able to create any voice we want. And if we so desire, we will be able to add features that Amazon, Apple, Microsoft and Google can only dream of.
Why it is the best bot to use right now
Uber has developed its own text-to-speech engine using an open source tool called OpenFTS. OpenFTS is design to provide speech synthesis functionality in a wide variety of languages for all kinds of software applications. Uber chose OpenFTS because it is very flexible and customizable. OpenFTS is base on the Open Source Speech Synthesis Toolkit (OSSSTK) and is license under the MIT License.
 How to use it
The Uberduck SDK is built on top of the OSSSTK. And includes a number of APIs that allow developers to access the features of the service. These APIs include:
TextToSpeech: This API allows developers to control the text-to-speech engine and provides a way to synthesize speech.
SpeechRecognition: This API allows developers to use the speech recognition feature of the service.
TextToSpeechSynthesis: This API allows developers to control the text-to-speech engine and provides a way to synthesize speech.
SpeechRecognitionSynthesis: This API allows developers to use the speech recognition feature of the service.
