Text to speech technology has come a long way in recent years. The so-called emotions are mostly pitch, speed and tonal variations of a computer generated voice. But OMG do they ever add quality to the narration. Check out Naoru in this short video...
Kaoru Flight Attendant Spokesperson
In the above video Kaoru is speaking with emotion "Cheerful." In the vertical video Kaoru is speaking with emotion "Friendly." We are now able to manipulate speed, pitch and tonal range of the text-to-speech voices. Which in turn gives the video creator more flexibility. and the avatars more liveliness.
Website tips for this post are:
1. Text to speech computer generated voices now come with emotions. There are 17 different emotions ranging from sad to happy to frightened to cheerfull, and friendly, unfriendly, shouting and general.
2. New HumanPal animated avatars have recently been released. These new avatars come in various sizes and dynamics. Kaoru is one of the first industry specific avatars out side medical that is. We also see new avatars for "construction" and "scrubs" related industries.
3. Camtasia is easier and faster than Davinci Resolve for editing animated videos.
In the widescreen video "Kaoru Animated Spokesperson Intro" was edited in Davinci Resolve 18.5 and took over 4 hours to finish. While the vertical video "Kaoru Flight Attendant" was edited in Camtasia Studio 2023 only took 2 hours to complete and is 30 seconds longer.
Don't forget to like and subscribe to the video channel. Thanks for watching, and have a safe flight.
