Music bed longer than your Short: YouTube Create caps it, Sume cuts it
YouTube Create says audio cannot exceed the video's length. A Sume Timeline render ends at audio.duration_seconds, with a soundtrack fade up to 10 s.

A music bed longer than your Short is a limit in YouTube Create but not in a Sume Timeline render: YouTube Create says audio tracks cannot exceed the length of the video, while a Sume Timeline render ends exactly at audio.duration_seconds and fades the bed out with soundtrack.fade_out_seconds, up to 10 seconds. Music generation itself takes no duration field, so you steer length in the prompt and cut the rest in Timeline.
YouTube's rule comes from Add & edit audio, read 2026-10-03. Sume's comes from Timeline 1.0, the Music Router and Music 1.0.
What does YouTube Create say?
On the audio page, YouTube lists split, volume, fade in and out, find beats, audio cleanup and delete for an audio layer. Under limits it says audio tracks cannot exceed the length of your video, and that licensed music from the Shorts Audio Library is removed automatically if you export a video longer than 15 seconds; upload directly to YouTube to use licensed music up to 60 seconds.
How does Music generation handle length?
Music 1.0 and the Music Router reject duration and duration_seconds. The docs steer length in the prompt: say "a 2-minute track" or use section markers like [0:00-0:30] Intro: .... A generation is a fixed $0.125 regardless of prompt length. The Music Router routes sume/music-auto to Lyria 3.5 today, with lyria-3.5 and lyria-3-pro as routable ids.
So a bed of 45 seconds for a 30-second Short is normal. You do not have to get the length right at generation time.
How do I cut it to the picture?
Set audio.duration_seconds to the Short's length. The render is exactly that long. The bed goes in soundtrack, with gain_db, loop, fade_out_seconds (up to 10) and duck_db (0 to 20, needs a real voice spine rather than silence). If the bed is shorter than the program and you do not loop it, the compiler leaves silence at the tail and returns a soundtrack_shorter_than_spine warning.
| Question | YouTube Create | Sume Timeline |
|---|---|---|
| Can the bed exceed the video? | No, audio cannot exceed video length | Yes, the render ends at audio.duration_seconds |
| Fade the end | Fade in and out timestamps on the layer | soundtrack.fade_out_seconds, up to 10 s |
| Duck under speech | Volume slider by hand | soundtrack.duck_db, 0 to 20 |
| Cost | Not stated on the page | $0.10 per ceil output minute, plus $0.125 per music generation |
curl -X POST https://api.sume.com/v1/timeline-1.0/render \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: bed-cut-001" \
-d '{
"audio": {"url": "https://media.sume.com/artifacts/artf_demo/vo.wav", "duration_seconds": 30},
"video": [{"source_url": "https://media.sume.com/artifacts/artf_demo/short.mp4", "start": 0, "duration": 30}],
"soundtrack": {"url": "https://media.sume.com/artifacts/artf_demo/bed.mp3", "gain_db": -12, "fade_out_seconds": 2, "duck_db": 8}
}'What Sume does not do
Sume does not offer licensed Audio Library tracks, so the 15-second removal rule does not apply to a bed you generated. It also has no beat-marker editor or audio cleanup step. Make sure you have the rights to any music you upload yourself.
Sources
Related posts
More in Use cases
- Music for an avatar video: pass the preview still as image_url
Approve an avatar preview, then send its preview_image_url to the Music Router as image_url so the track matches the frame. Steps, limits and the $0.125 cost.
- Nano Banana 2 catalog photos: draft at 0.5K, finish at 2K
Cut catalog image cost by drafting at 0.5K and rendering only approved shots at 2K with Nano Banana 2; vendor rates and the Sume resolution tiers.
- Narrate a 3-minute Short: Sume TTS, word timings and 60 s caption cuts
YouTube allows three-minute Shorts. A plan with Sume: one TTS request under 20,000 characters, word timings, and caption jobs in pieces of 60 seconds or less.
- Narrate an 80,000-word novel with AI TTS: $23 in 34 requests
An 80,000-word novel is about 480,000 characters, quoted at $23.00 on Sume TTS in 34 requests of up to 14,400 characters, roughly 10 hours of audio.
Written by Sume