How do I make one intro bumper and reuse it in every course lesson?
Make a 5-second bumper once ($0.83 with a sting), then add it to 24 eight-minute lessons at $0.82 each: $20.51 for the course on Sume.

Make the bumper once, keep the file, and add it to each lesson with a render. The bumper is a title card image ($0.075 at medium on ideogram/ideogram-v4.5), animated for 5 seconds ($0.63 at 720p on gemini-omni-flash-1.1), plus a music sting ($0.125): $0.83 in total, one time. Each lesson then costs $0.01 to detach its audio, $0.01 to join the sting and the lesson audio, and $0.10 per started minute to render. For an 8-minute lesson that is $0.82, and for 24 lessons the course comes to $20.51.
Make the bumper once. Every generation is a new random result, so a bumper regenerated per lesson looks different each time, and a branded intro that changes is not branding.
Design the bumper for reuse
A good bumper is 3 to 5 seconds, carries the course name and the colours, and has no speech. Leave the module number out of the animated clip and burn it in later with caption cues if you want one per module. Then one clip serves every module, and only the text changes.
Pick the aspect ratio of your lessons first. Omni takes 16:9 or 9:16, so make a 16:9 bumper for landscape lessons and a 9:16 one if you teach on a phone.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: course-bumper-v1" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "Slow light sweep across the title card, subtle grain, no camera shake",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": false,
"frame_images": [{ "type": "image_url",
"image_url": { "url": "https://media.sume.com/artifacts/artf_demo/titlecard.png" },
"frame_type": "first_frame" }]
}'Why each lesson needs a join
A Timeline 1.0 render needs one audio spine for its whole length, and a silent bumper has no audio. The fix is to make the spine yourself. Detach the lesson's audio from its video with POST /v1/audio-detach ($0.01, source up to 1,800 seconds). Then call Timeline audio with operation: concat and two parts: the sting, cut to 5 seconds with duration: 5, and the lesson audio. The result returns segments[] with each part's offset, and that is the audio for the render.
In the render, the bumper is the first video[] slot (start 0, duration 5) and the lesson recording is the second (start 5). Check warnings[] on the result.
curl -X POST https://api.sume.com/v1/timeline-1.0/audio \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: lesson-07-spine" \
-d '{
"operation": "concat",
"parts": [
{ "url": "https://media.sume.com/artifacts/artf_demo/sting.wav", "duration": 5 },
{ "url": "https://media.sume.com/artifacts/artf_demo/lesson07.wav" }
]
}'The minute boundary
Timeline 1.0 bills $0.10 per started output minute. A lesson of 7 minutes 30 seconds plus the 5-second bumper is 7:35, which is 8 started minutes, $0.80. A lesson of exactly 8:00 plus the bumper is 8:05, which is 9 started minutes, $0.90. Check each lesson's length: if one is a few seconds over a minute boundary, trimming a second of silence at the start saves ten cents.
That is the only real extra cost of reuse. The bumper is a file, and adding it to a render is not a new generation.
What the course costs
- The render is the main cost, and it would be there without a bumper if you re-export every lesson anyway.
- A new season with a new bumper costs $0.83 and leaves the old lessons alone.
- Burn module numbers with caption cues at $0.20 per lesson if you want them.
| Step | Unit | Price | Course total |
|---|---|---|---|
| Title card, ideogram-v4.5 medium | per image | $0.075 | $0.075 |
| Bumper, omni 720p, 5 s | per clip | $0.63 | $0.63 |
| Music sting | per track | $0.125 | $0.125 |
| Detach lesson audio | per job | $0.01 | $0.24 for 24 |
| Join sting and lesson | per job | $0.01 | $0.24 for 24 |
| Render, 8 started minutes | per started minute | $0.10 | $19.20 for 24 |
| Total | $20.51 |
Sources
Related posts
More in Use cases
- How to make a pep talk audio track with music: voice, bed and render
A 90-second pep talk with a music bed is one TTS job, one Music Router job and one render: about $0.39 on Sume. Suno Speech beta does it in one pass.
- Pick clip lengths from a voice-over script: one sentence per clip
Turn a voice-over into clips: measure each voiced sentence, round up, and pick the models whose duration window contains it. Windows for six Sume models.
- How do I turn one podcast episode into five quote clips for social?
Transcribe the episode in 10-minute chunks, split five quotes out, put the cover still under each and burn captions: $1.80 for a 28-minute episode on Sume.
- Post-call recap video with an AI avatar for prospects: script and cost
After a sales call, send a 30-second recap clip from a Sume avatar. Script structure, cost at standard, plus and max, and how to keep it honest and reviewed.
Written by Sume