It’s magic

Text2Video and Voice2Video are software applications based on the following principles:

1. Receipt of a text or of a voice message

2. Conversion of the text into speech. Here, the text is transmitted to a specific program, creating a synthetic audio file (e.g. a .WAV-file). For a voice message, the message file is processed by a automatic speech recognition (ASR) software.

3. The animation of the message is based on the TTS- or the ASR-process. Both engines provide information on the used phonemes, pitch information, their duration and more. A video file is generated.

4. The video file and the audio file with the message are combined into the final animation output file.

Our animation technology has been developed to meet the following requirements:

• Highly realistic speech motion and synchronicity
• Efficient execution so that the technology can be used on almost all mobile devices
• It can easily be applied to any photograph
• Mix with other facial expressions such as smiling, nodding etc.
• Include teeth and tongue model