The Vocal Synthesis channel on YouTube trains text-to-speech models using publicly available celebrity voices. Then using this new computer-generated voice, the celebrities “recite” various scripts. For example, the above is Jay-Z rapping the “To be, or not to be” soliloquy from Hamlet, but it’s not him.
Text-to-speech models trained on celebrity voices
Projects by FlowingData See All →
What are the ingredients that make each cuisine? I looked at 40,000 recipes spanning 20 cuisines and 6,714 ingredients to see what makes food taste different.
Counting Happiness and Where it Comes From
Researchers asked 10,000 participants to list ten things that recently made them happy. I counted and connected the dots.