Whole-song AI music video: a 3-minute video for $11.68
A full 3-minute music video on Sume: one Lyria 3.5 track, 18 ten-second Wan 3.0 shots at 480p and a 3-minute Timeline render for $11.68.
Whole song, not a 15-second clip
A song is three minutes, but video jobs are seconds long. The plan is track first, then 18 shots of 10 seconds cut to the verse and chorus, then one Timeline render with the track as the soundtrack.
| Route | 18 shots or 6 long jobs | Track | Timeline 3 min | Total |
|---|---|---|---|---|
| Wan 3.0 480p, 10 s shots | $11.34 | $0.125 | $0.30 | $11.77 |
| Wan 3.0 720p, 10 s shots | $22.50 | $0.125 | $0.30 | $22.93 |
| Seedance 2.5 480p, six 30 s jobs | $48.42 | $0.125 | $0.30 | $48.85 |
Workflow
Put tempo and structure in the Lyria prompt, since length is controlled by the prompt. Draft all shots at 480p, keep the best, and re-render only chosen shots at 720p.
Generated video does not lip-sync a vocal, so use performance-free visuals: scenery, dance, objects and abstract motion.
Sources
Related posts
More in Use cases
- Wine bottle reveal clip: 6 seconds of Wan 3.0 from a label photo
Animate a bottle photo into a 6-second reveal with wan-3.0 on Sume: 38 cents at 480p, 75 cents at 720p, $1.50 at 1080p. Why the label needs checking.
- How do I make a winter tire changeover promo video for my garage?
Three 6-second Wan 3.0 clips, a 420-character voiceover, a duck-under music bed and booking captions for a garage: $2.695 on Sume at 720p.
- Write a lip-sync script in 5 to 14.8 second beats (H3 Max voice-over)
MiniMax H3 Max lip-sync on Sume takes audio of 5 to 14.8 seconds. Write the script in beats that fit the window, then voice each beat; the price per beat.
- Write the music brief after the voiceover, using TTS timestamps
Lyria on Sume takes no duration field, only time ranges in the prompt. Generate the voiceover first, read its word timings, then write the section markers.
Written by Sume