Results Summary

• Audio: CNN anchor’s Audio appears to be AI generated using RVC cloning techniques.
• Video: Frames appears to be genuine. Lip movements DO NOT match the Audio.

A. Detailed Audio results

• AudioSpoof detection models indicate with a high level of confidence that the audio file is AI-generated.
• The audio closely resembles the voice of CNN anchor Jake Tapper, strongly suggesting that Retrieval Voice Conversion (RVC) technology may have been used to replicate their vocal characteristics.

B. Detailed Video results

• Frame deepfake detection model find the video frames to be genuince & without any AI manipulation
• There is a clear mismatch between lip movements in the frames & the audio.