Results Summary

• Audio appears to be fully AI generated using RVC cloning techniques.
• Video frames appear to be real. Lip movements DO NOT match the Audio.

A. Detailed Audio results

• 2 out of 2 AudioSpoof detection models predict the Audio file to be AI generated with high confidence.
• The audio sounds very similar to Mohammad Yunus, which gives strong indication that Retrieval Voice Conversion (RVC) based cloning has been done to emulate their voice.

B. Video results

• There is no lip sync between the frames in the Video & the Audio content, hence no scope of AI manipulation.
• Possible source video - https://www.youtube.com/watch?v=wBYq20eWrpM