lex2029/vlogme-avatar-bridge 🖼️✓ → 🖼️

▶️ 43 runs 📅 Jul 2026 ⚙️ Cog 0.19.3 🔗 GitHub

image-to-video lipsync video-auto-captioning

Performance

271.1sTypical run time

43Total runs

About

Create a vertical talking-avatar video from a centered photo and speech audio.

Example Output

Output

Performance Metrics

271.08s Prediction Time

287.37s Total Time

All Input Parameters

{
  "audio": "https://replicate.delivery/pbxt/PPAfrLR034WwnIkDrYxDT2fKYlTjRFh3oNSPjcTTKtACorNt/download.mp3",
  "avatar_image": "https://replicate.delivery/pbxt/PPAfrHC0CIGnEE8pe8xlALqTW1Q8hWlxaB371maYltJN4aTE/a290eff83546c753d1eba59b306a194075a3c0318330db99261f680ab1138958.jpg",
  "live_subtitles": true
}

Input Parameters

audio (required) Type: string
avatar_image (required) Type: string
live_subtitles Type: booleanDefault: true: Burn word-level subtitles into the final video

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

[replicate-avatar-bridge] submitting VlogMe render job: vertical_9_16=1 watermark_top=Created by VlogMe.AI
[replicate-avatar-bridge] VlogMe job accepted: id=0679f6db-87fc-43bc-b1c6-93e2189b7f30 status=preparing estimated_seconds=37
[replicate-avatar-bridge] VlogMe status: preparing progress=10 stage=transcribing_audio
[replicate-avatar-bridge] VlogMe status: preparing progress=55 stage=transcribing_audio
[replicate-avatar-bridge] VlogMe status: queued progress=0 stage=
[replicate-avatar-bridge] VlogMe status: running progress=1 stage=prepare
[replicate-avatar-bridge] VlogMe status: running progress=23 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=25 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=28 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=30 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=33 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=39 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=41 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=44 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=47 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=52 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=55 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=58 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=61 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=66 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=69 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=70 stage=inference
[replicate-avatar-bridge] VlogMe status: running progress=82 stage=encode
[replicate-avatar-bridge] VlogMe status: completed progress=100 stage=
[replicate-avatar-bridge] downloading completed VlogMe output

Version Details

Version ID: 767500daee487e15eb0757e712b04d14bb4f85fd06d1c90d64e1702130366c96
Version Created: July 15, 2026

Run on Replicate →