TXTOmedia video localization

TXTOmedia video localization is part of our video automation technology that turns structured content into videos. The SaaS-technology ties into your existing (C)CMS platform, where often localized versions of your content originate or get localized. From here the localized structured DITA and XML content is brought to the TXTOmedia platform to be automatically transformed into localized videos.

Our VoiceFactory offers over 60 languages and hundreds of different voices.
Please check The Voice Factory for an overview of all available languages and voices. You can even test the default voice samples here.

Another feature of the TXTOmedia technology is to offer your content in one language and get your videos back in multiple languages at once. During processing the video, TXTOmedia sends your original content for translation at the same time, before transforming the once localized content to videos as well. How your content gets translated and localized is open for discussion; it can be based on Machine Translation, Human Translation, or a hybrid form. With the videos, we send the localized editable content back to your (C)CMS as well for future references and to enable adjustments on-the-fly.

To find out more, contact us or book a demo.

VoiceFactory: Languages & Voices

TXTOmedia’s VoiceFactory creates speech from text in over 60 languagues. Combining technologies and services of Google, Amazon, Microsoft and IBM, TXTOmedia is able to offer all available languages and the widest range of voices out there.

Our customers are free to choose whatever voices they prefer without worrying about the various service providers. Also we are able to train and tweak each of these voices based on our SSML compliant interface.To test all voices with their default settings, go to The VoiceFactory.

Also Human voices

Although synthesizer (artificial) voices are preferred due to processing time, it is possible to use and reuse human voices too.

Traditional human voices
The use of traditional voices and voice actors is possible. The recorded fragments are stored in a database and refered to via metadata. The result is the most natural sound one can expect. The method is less flexible though, and less cost-effective.

Automated human voices
There is also the option to record real human voices and load them into the synthisizer. From that moment onwards you can leverage the real human voices as were it artificial ones. Advantages are quality, flexibility and costs.