FakeYou

FakeYou provides text-to-speech and text-to-video generation by employing voice cloning models trained on a vast library of celebrity and character voices. The core mechanism is a TTS engine that synthesizes audio from user-submitted text in a selected voice. For video, the system utilizes a lip-sync model to animate a static image, matching the mouth movements to the generated audio track. Users input text and can upload source images (JPG, PNG), with the final outputs delivered as audio (MP3) or video (MP4) files. The tool is built for content creators, animators, and social media managers focused on entertainment and parody. A typical workflow involves a creator generating a short audio monologue in a recognizable voice for a satirical animated short. Another use case sees a social media manager producing a lip-synced video clip of a public figure for a viral marketing campaign on TikTok or Instagram, layering the generated MP4 file directly into their social media scheduler for posting.