ESPESY voice recordings

With our R&D project ESPESY, we are making speech synthesis emotional and communication with computers more natural. Whether anxious, excited or angry…the voice assistant will soon have the right emotion ready for every situation.

About 40,000 voice recordings in seven different emotions were recorded for this purpose in our speaker cabin at WE16 in Hamburg over the last few months. Now we are training our AI based system to speak with different emotions. The future application possibilities for this are countless: from emotional voice assistants and authentic text to speech generators to individual brand voice systems for our clients.

The project is progressing! We are already looking forward to tell you more about it and to eventually share the results with you.

ESPESY is funded by the Federal Ministry for Economic Affairs and Energy and the ZIM – Central Innovation Programme for SMEs.