- Joined
- Mar 30, 2023
We have an AI that can replicate a voice just by hearing a few lines
We have an AI that can recognize spoken words
We have an AI that can translate text to a different language while preserving key context
How hard would it be to make an AI that can make a dub in the exact same voice as the original voice actor, and preserving the intonations and emotions conveyed in each word?
And while we're at it, can we use an AI to edit the video to lip sync it with the audio? And maybe develope a video format that preserves the alternative lip sync to play depending on the language chosen?
We have an AI that can recognize spoken words
We have an AI that can translate text to a different language while preserving key context
How hard would it be to make an AI that can make a dub in the exact same voice as the original voice actor, and preserving the intonations and emotions conveyed in each word?
And while we're at it, can we use an AI to edit the video to lip sync it with the audio? And maybe develope a video format that preserves the alternative lip sync to play depending on the language chosen?