Clone Me YTD — Staging

Private staging storage. Uploaded media and extracted clips stay outside the public web directory. Use HTTPS and keep the staging token private. Only process videos you own or have permission to download.

Staging access

Enter the token configured on the server.

Not connected

Avatar photos

Upload up to 20 clear photos for the future digital-you pipeline.

0 selected

＋

Drop photos hereor click to browse · JPG, PNG, WEBP

Voice sample

Use a clean 2–5 minute recording. WAV is preferred.

No file

◉

Choose a voice sampleWAV preferred · MP3, M4A, OGG and FLAC accepted

Reference video upload

Upload a video you own or have permission to process. The same speech + visible-face narrator detection is used.

No file

▶

Drop a video hereor click to browse · MP4 recommended · uploads are chunked to avoid request-size limits

YouTube narrator extractor

Paste a YouTube video you own or have permission to process. The app finds speech that overlaps with a visible face and exports matching clips.

Ready

Video generation

Next: use these reference assets for voice, avatar motion, lip-sync and video generation.

01 Voice clone

02 Avatar motion

03 Lip sync

04 Compose video