Target RTVC pretrained RTVC finetuned 1k RTVC finetuned 5k Overdub Resemble AI
*RTVC = Real-Time-Voice-Cloning

The first column represents a target speaker`s voice sample, the other columns each refer to a tool (and model in case of RTVC) that was used to create synthetic voice of the target speaker and the recordings synthesized using given tool.