ONDEWO Text-to-Speech (T2S) Platform

Your text gets a unique voice with the sound most appealing to your customers.

  • Your customers will interact with a friendly human voice
  • Choose the language and dialect of your voice that fits best your needs and preferences
  • Create your unique artificial human voice reflecting your brand and company values

What you gain

Our Text-to-Speech platform offers a reliable voice generation in the voice you like best. With provided voice recordings, a new one can get added specified to your company.

Multiple-languages and dialects available

Our AI Agent can speak in a range of different voices and accents in multiple languages The range of our different options gets expanded continuously.

State of the art voice generation

With our newest deep learning algorithms and our unique approach for processing audio, the voices sound as human as possible, improving evermore.

Create your own AI voice

Your company and brand is unique hence also the voice of your AI solution should be. Our platform allows the creation of a new voice based on only 5-8 hours audio from your preferred human voice. 


Convert your text into spoken word

Listen to some examples for voice synthesis. By the way, if you are tired of listening to the same cloud provider voices all the time and want to make a difference for your customers, we also offer the creation of your own unique AI voice for your brand based on audio recording in our audio studio at our office.


Important Features

What makes it special

Unique voices

A new voice can get created based on 5-8 hours of audio recordings, so approximately 3 days of audio recording of your preferred voice in the ONDEWO audio studio at our office. The dataset gets used for training the AI-Agent, to synthesis a humanlike speech and pronunciation.

Human-like voice

The speech gets synthesized with the newest neural approaches. The result is that the voice is non-robotic, making it more comfortable for humans to interact with it.

High speed text to audio synthesis

Text is synthesized to human voice approximately 5-6 times faster than cloud platforms. This real-time capability is especially important for telephone automation and voice assistants to allow seemingly natural interactions.

Two synthesizes modes: “real time” and “batch file”

Real-time mode synthesizes text while listening to text streamed to the platform (e.g. via web socket interface). This synthesized audio is continuously streamed back. Batch file mode synthesizes text to audio based on text input sent to the platform that returns an audio file.

Quick and easy integration into products and services

All platform capabilities are easy to integrate into your products and services via ondewo-client libraries for various programming languages (e.g. Python, Nodejs, Angular, JavaScript etc.) and gRPC Remote Procedure Calls (“GRRPC”).

On-premise and cloud hosting

All features are available on both versions. The on-premise solution easily installs on all operating systems with standard Docker deployment environment on your own IT Infrastructure. Furthermore, it allows for a higher degree of data protection and control. With the cloud option, there is no maintenance needed as it gets provided by ONDEWO. The cloud option is billed on a usage basis. 


What else is new

Register here for the ONDEWO newsletter. You will be up to date, and you will always be the first to know about new products and solutions as well as other news.

Get Started

Get started right away!

What challenge is your company facing? An ONDEWO expert will be happy to support you in finding the best solution!

Become an ONDEWO partner

Get to know our Products

See all industry solutions