A holiday music video from one Lyria track: 18 clips, about $23.50
Lyria track $0.125, eighteen 10-second Omni Flash clips at 720p $22.50, Timeline $0.30, captions $0.60. Total about $23.53 for 3 minutes.
A 3-minute holiday music video built from one generated song costs about $23.53 on Sume. That is $0.13 for the Lyria 3.5 track, $22.50 for eighteen 10-second clips from Gemini Omni Flash 1.1 at 720p, $0.30 to assemble them on Timeline and $0.60 for three burned-in lyric caption jobs.
The track has to exist before you cut anything, because the Timeline job takes one audio spine and places video slots on top of it. So the order is song, clips, render, captions.
Step 1: the song at $0.125
Music Router charges a fixed $0.125 per accepted generation, whatever the prompt length. Length is controlled in the prompt, for example 'a 3-minute track' or section markers like [0:00-0:30] Intro. The API rejects a duration field. sume/music-auto picks the engine, which is Lyria 3.5 today.
Step 2: eighteen clips
At 10 seconds each, 18 clips fill 180 seconds. Omni Flash 1.1 at 720p bills $0.125 per second, so one clip is $1.25 and 18 are $22.50. Because the model accepts a first frame and reference images, keep the same singer or the same snow-globe prop in every call so the cuts feel like one video.
| Step | Unit price | Quantity | Total |
|---|---|---|---|
| Song, Music Router | $0.125 | 1 | $0.13 |
| Clip, Omni Flash 1.1, 10 s, 720p | $1.25 | 18 | $22.50 |
| Timeline render, per output minute | $0.10 | 3 | $0.30 |
| Standalone captions, up to 60 s each | $0.20 | 3 | $0.60 |
| Total | $23.53 |
Step 3 and 4: assemble and caption
Timeline renders $0.10 per output minute, rounded up, so three minutes are $0.30. Every URL must already be a Sume-hosted artifact, so import first. The standalone caption job covers videos of at most 60 seconds at $0.20 under the current fixed estimate, so a 3-minute video needs one caption job per 60-second part, not one. Captioning the 3 parts costs 3 × $0.20 = $0.60, which gives the total of $23.53.
If lyrics are not needed on screen for the full song, caption only the chorus and keep the total near $23.
Cuts you can make
The per-clip rounding is already included above. Re-render only clips that fail, not the video.
- Drop to 480p clips if the video is a lyric visualizer: Wan 3.0 at 480p bills $0.0625 per second, so 180 seconds cost $11.25.
- Reuse clips across songs: a 30-second chorus loop costs 3 × $1.25 = $3.75 and can cover two verses.
- Render only a 60-second cut for the Short (YouTube allows Shorts up to 3 minutes), at one third of the clip cost.
Sources
Related posts
More in Use cases
- Music visualizer clip: MiniMax H3 Max, image plus audio reference
Make a 10-second visualizer from cover art plus a track excerpt with minimax-h3-max on Sume: $1.00 at 768p; audio alone is not a valid reference.
- Napkin sketch to product render: one reference on GPT Image 2.5
Turn a photographed napkin sketch into a product render with one input reference on GPT Image 2.5. Set aspect_ratio auto to keep the shape. Code and prices.
- New Year countdown video music: build to midnight with a timed prompt
Write a timed Lyria 3.5 prompt that builds for 50 seconds and hits at midnight. $0.125 a take on Sume, then a Timeline render at $0.10 under your countdown.
- Nine product angles as references: MiniMax H3 Max on Sume
How to send up to nine product photos as reference images to minimax-h3-max on Sume, what the vendor limit is, and where Sume's own limits live.
Written by Sume