I researched and developed a TTS system that is able to control the prosody of speech in a fine-grained level, so that users can generate speech with the prosody they want. I contributed to the release of this fine-grained, controllable TTS system, which has been made available as an in-company web service. Notably, it was used in official guide videos for NCSOFT's games, enhancing the user experience.
Below is an example of an official guide video for Trickster-M, one of NCSOFT's games. (Speech subtitled with red background is generated using the TTS system with fine-grained prosody control.)