
Kling motion control 23-second clip: $3.62, and 22.4 s bills as 23
Kling 3.0 Motion Control on Sume is $0.1575 per output second: a 23-second driving video is 23 x 0.1575 = $3.62, and a 22.4 s one is rounded up to 23.
Sume media tools by API: trim, filter, captions, frames, inspect, speech-to-text, upscaling, background removal, transitions, and Timeline assembly.
Start with: Video editing API limits: Sume media tool caps in one table

Kling 3.0 Motion Control on Sume is $0.1575 per output second: a 23-second driving video is 23 x 0.1575 = $3.62, and a 22.4 s one is rounded up to 23.

LinkedIn allows videos up to 30 minutes. Video inspect takes 1,800 seconds and 24 stills per call, so at[] with 37.5 + 75k covers the whole file in one job.

Timeline 1.0 allows audio.duration_seconds up to 1800 and 200 video slots per render. At $0.10 per minute the ceiling is 30 x $0.10 = $3.00.

Sume music takes an optional image_url and no duration field. Put "a 12-second track" in the prompt; the job is a flat $0.125 whatever the image or the length.

YouTube says most songs run up to 90 seconds in a 3-minute Short. Join 90 s of song to 75 s of other audio with timeline audio, then render for $0.31.

Spark Ads list .mp4 or .mov with no duration limit; non-Spark lists five containers and 10 minutes. Sume trim and Timeline write MP4, so both fit.

YouTube Shorts can run up to three minutes. A 200-second take needs one exact video-trim job (start 0, duration 180) at $0.02. Here is the request.

Video filter takes up to 8 dim/crop ops plus a filters-only graph of 2,048 characters and 32 filters. See what is allowed, what is refused, and the free check.

The inspect frames program caps at 24 stills and fps at 2. For a 60-second clip, fps 0.4 fills all 24 slots, 2.5 seconds apart, centered in each bin.

transcribe true in video inspect adds STT at $0.01 per audio minute. An 8-minute clip is $0.08 plus compute; duration_seconds hints up to 600 s of reserve.

YouTube's upload page asks for 384 kbps stereo, 128 mono, 512 for 5.1, at 48 kHz. For 180 seconds that is 8.64, 2.88 or 11.52 MB; Sume detach can write 48 kHz.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 1,000 product photos is $22.50. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 10,000 product photos is $225.00. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 100 product photos is $2.25. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 2,500 product photos is $56.25. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 250 product photos is $5.63. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 40 product photos is $0.90. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 5,000 product photos is $112.50. Rate read 2026-10-09.

Remove background (RMBG 1.0) is $0.0225 per image in the Sume catalog, so cutting out 500 product photos is $11.25. Rate read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 10-minute audio spine is $1.00. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 15-minute audio spine is $1.50. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 20-minute audio spine is $2.00. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 25-minute audio spine is $2.50. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 3-minute audio spine is $0.30. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 30-minute audio spine is $3.00. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 5-minute audio spine is $0.50. Maximum 1,800 seconds per render. Read 2026-10-09.

Sume Timeline 1.0 charges $0.10 per output minute, rounded up: a 8-minute audio spine is $0.80. Maximum 1,800 seconds per render. Read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 1,000 images is $200.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 1 minute of footage is $0.54. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 10 images is $2.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 10 minutes of footage is $5.40. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 100 images is $20.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 120 minutes of footage is $64.80. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 25 images is $5.00. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 250 images is $50.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 30 minutes of footage is $16.20. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 300 minutes of footage is $162.00. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 40 images is $8.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 5 minutes of footage is $2.70. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 500 images is $100.00. Rate read 2026-10-09.

Image upscale 1.0 is $0.2 per image in the Sume catalog, so upscaling 60 images is $12.00. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 60 minutes of footage is $32.40. Rate read 2026-10-09.

Video upscale 1.0 is $0.009 per second in the Sume catalog, so upscaling 600 minutes of footage is $324.00. Rate read 2026-10-09.

Sume refuses Korean text on the slam, punch and tiktok-green caption styles with a 400. Use black-outline, korean-ad or another Hangul style; $0.20 a job.

A silent clip fails Sume video captions with caption_no_speech. Send cues with text, start and end to burn overlay text instead. One job, $0.20 up to 60 s.

Center-crop a 16:9 clip to vertical with Sume video filter: the crop fractions, the arithmetic, and why 1280x720 falls under TikTok's 540x960 minimum.

Sume audio detach with channels mono and sample_rate 16000 gives the speech-to-text shape. A 10-minute video costs $0.01 to detach plus $0.10 to transcribe.

Sume POST /v1/video-frames extracts up to 24 exact stills at source size. Always async (202); a failed instant gives a null url and the job still succeeds.