Comment Comment by 100ms I thought to try voice cloning with dots.tts ( https://huggingface.co/spaces/rednote-hilab/dots.tts ), the result is pretty good, but likely wouldn't be fast enough to use on a quasi-realtime basis:Input clip: https://vocaroo.com/19QtEPtwTjOSPrompt text: There are 14 varieties of tomato soup available from this replicator. With rice, with vegetables, Bolian style, with pasta specify hot or chilled.Output: https://vocaroo.com/1f3XuQQoSzwB parent 100ms 3 months ago
Input clip: https://vocaroo.com/19QtEPtwTjOS
Prompt text: There are 14 varieties of tomato soup available from this replicator. With rice, with vegetables, Bolian style, with pasta specify hot or chilled.
Output: https://vocaroo.com/1f3XuQQoSzwB