Media tools
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
YouTube AI label and captions: burned-in subtitles on a real clip
YouTube's disclosure page exempts caption creation. Burning captions into your own footage with Sume is a $0.20 job for a clip up to 60 seconds.
True pixel art from an AI image: quantize to 16 colors in Pillow
AI models draw pixel-art looks at full resolution. Downscale with NEAREST, quantize to 16 colors without dither, and upscale clean to get real pixel art.
Two-color duotone poster from an AI image with ImageOps.colorize
Turn a Sume image into a duotone: grayscale, autocontrast, then ImageOps.colorize with a dark and a light brand color. Code and ink pairs inside.
Put a logo or lower third over a talking avatar video with compose
Timeline compose overlay places a Sume-hosted still over an avatar clip, at the top, center or bottom. $0.02 flat per job. The layout keys and a request.
Soft drop shadow under an AI product cutout with Pillow
Give a transparent product PNG from Sume a soft drop shadow: copy the alpha, blur it, offset it, tint it, then composite. Parameters for subtle and heavy looks.
Crop a 16:9 AI clip to 21:9 with video filter: height 0.762, y 0.119
Cut a 16:9 Wan 3.0 or Kling 3 clip to a 21:9 frame for $0.02: crop width 1, height 0.762, y 0.119. Compared with generating 21:9 natively on Sume.
Use a MAI-Voice-2.1 clip as avatar audio? Sume needs its own file
A talking still on Sume takes Sume-hosted audio under 10 MB. A MAI-Voice-2.1 clip sits elsewhere, so make the line with Sume TTS instead. Sizes and limits.
One voice-over under ten AI shots: Timeline spine and start times
Put one narration track under ten AI video shots on Sume Timeline: video[0].start is 0, later starts increase, and the last shot may end up to 0.5 s early.
Restaurant menu video music: a 30-second brief and cost
What to ask Lyria for under a 30-second restaurant menu video: tempo, instruments, a clean ending and the $0.225 audio cost on Sume with a Timeline render.
Timeline output size for 21:9 and 16:9 clips: default is 1080x1920
Sume Timeline renders 1080x1920 portrait unless you set output.width and height: even integers, 256 to 2160. Sizes that work for 21:9 and 16:9 AI clips.
Fades between 2-second AI shots: the 1 s cap and the 8-fade chain
Joining 15 two-second Wan 3.0 shots on Sume Timeline: a fade can be at most 1 s, at most half of the shorter shot, and 8 chained fades are refused. Python.
Baby shower video music: a gentle 90-second slideshow bed
Pick a gentle instrumental for a 90-second baby shower photo slideshow: one generation and a two-minute render, $0.325 on Sume.
Coffee roaster brand video music: a 40-second lofi bed
Brief a warm 40-second lofi bed with vinyl texture for a coffee roaster brand video: one generation and a one-minute render, $0.225 on Sume.
Coffee roaster holiday video: caption in your brand colour with design
Caption a roaster's holiday video in a brand colour with `design.colors.active`, then restyle twice without a second transcription: three looks for $0.60.
Comedy skit music: one bed and two stings with AI music
Score a 45-second comedy skit with one light bed and two short stings: three Music Router generations at $0.125 each plus a Timeline render, $0.475 in total.
Corporate onboarding video music: a 5-minute ducked bed
Add a 5-minute instrumental bed under onboarding narration with duck_db in Timeline: one generation and a 5-minute render, $0.625 on Sume.
Day of the Dead video music: a 60-second tribute brief
Brief an instrumental bed for a 60-second Day of the Dead tribute video with guitarron, trumpet and harp: one generation, one render, $0.225 on Sume.
Dental clinic explainer: a calm AI music bed and its cost
Brief a calm, non-medical-sounding instrumental for a 90-second clinic explainer, duck it under the voiceover and see the audio cost: $0.325 on Sume.
Documentary underscore with AI music: a 3-minute brief and cost
How to brief an instrumental underscore for a 3-minute documentary with narration: one Lyria request, a ducked bed in Timeline, and the full audio cost.
Esports highlight reel music: a 45-second hype bed with a drop
Brief a 45-second esports highlight with a drop at 0:20: one Lyria generation at $0.125, a Timeline render and a duck under game commentary.
Graduation video music: a 2-minute anthem with a build
Brief a 2-minute graduation video bed with a build to a triumphant moment at 1:20 for the diploma reel: one generation and a render, $0.325 on Sume.
Headphones listing video: spec card on the left, clip on the right
Build a 16:9 listing video for headphones with Timeline compose: a vertical stack with the spec card left, 0.35 ratio, clip on the right, $0.02 a shot on Sume.
Hotel lobby screen music: a 2-minute welcome video loop
Make a 2-minute welcome video with a soft jazz-lounge bed for a hotel lobby screen: one generation and a two-minute render, $0.325 on Sume.
Perfume unboxing captions with the scent names spelled right
Fix mis-heard product names in auto-captions by sending script_text: Sume keeps the speech timings and burns your spelling, $0.20 per clip up to 60 seconds.
Pet adoption video music: a 30-second hopeful shelter bed
Brief a 30-second hopeful acoustic bed for a shelter's pet adoption appeal: one generation and a one-minute render, $0.225 on Sume.
Singles' Day sale videos: four 15-second AI music variants
Make four 15-second sale videos with different music for a Singles' Day 11.11 promotion: four Music Router generations and four renders, $0.90 on Sume.
Sneaker drop teaser: six clips, slideup cuts, one Timeline render
Cut six sneaker clips into one 18-second drop teaser with slideup transitions and a music bed: one Sume Timeline render, $0.10, with a free plan call first.
Tech review intro music: a 20-second sting and bed
Make a 20-second synth intro bed for a tech review channel that you can reuse in every video: one generation and a one-minute render, $0.225 on Sume.
Thanksgiving recipe video music: a 60-second acoustic bed
Add a 60-second warm acoustic bed under a Thanksgiving recipe video with a lift at the plating shot: one generation and a one-minute render, $0.225 on Sume.
Wine tasting video music: a 2-minute refined, quiet bed
Brief a refined 2-minute instrumental for a wine tasting video that stays under the host's voice: one generation and a two-minute render, $0.325 on Sume.
Winter coat lookbook clip with a size and care plate over the footage
Put a still size-and-care plate over a coat clip with Timeline compose overlay: width_ratio, margin_ratio and position set the plate, $0.02 a clip on Sume.
Yoga class video music: loop a 2-minute bed for 20 minutes
Generate one calm 2-minute ambient bed and loop it under a 20-minute yoga video with Timeline: one generation plus a 20-minute render, $2.125 on Sume.
Avatar clip frame rate: Griffin 25 fps vs Fabric vs H3 Max
Tavus says Griffin streams 8-frame latents at 25 fps. Sume's docs say Fabric is 25 fps and H3 Max must be measured. Probe a clip with video-inspect.
60 fps 3-minute YouTube Short: 12 Mbps is 270 MB vs 180 MB at 30 fps
A 3-minute Short at YouTube's 12 Mbps 60 fps rate is about 270 MB, against 180 MB at 8 Mbps. Work out the sizes, and when Sume should not render 60 fps.
720p 3-minute YouTube Short: 112.5 MB at 5 Mbps, render 720x1280
YouTube's recommended 720p bitrate is 5 Mbps, so a 180-second Short is about 112.5 MB. Render 720x1280 in Timeline 1.0 for the same $0.30 as 1080p.
23.976 fps clip for a YouTube Short: omit output.fps in Sume
Sume's output.fps accepts 24, 25, 30 and 60. For a 23.976 fps source, omit it so the render matches the source, because YouTube keeps native frame rates.
Can a 1080x1080 square video be a 3-minute YouTube Short?
Yes: YouTube's help page says a Short can run up to 3 minutes if it is square or vertical. Render 1080x1080 in Sume Timeline 1.0 for $0.30 at 180 seconds.
Kling motion control reference over 30 seconds: trim it first
Sume's Kling motion control takes a duration_seconds of 1 to 30. For a longer dance or walk clip, cut a 30-second range with video trim, then submit that.
Silent reference clip: reference_ingest's -60 LUFS gate and STT
reference_ingest marks a clip audio.silent at -60 LUFS or below and skips STT, so a silent reference costs no transcript. What to do next: plan new music.
TikTok in-feed ad minimums: 540x960 and 516 kbps for a Sume MP4
TikTok non-Spark in-feed ads need 9:16 at 540x960 or more, 500 MB or less and 516 kbps or more. Sume's default 1080x1920 clears the size floor; check bitrate.
TikTok Shop main image: no text, borders or stickers checklist
TikTok Shop wants a clean main image: white background, no watermarks, borders, promo text or stickers, 5+ images for Good. A checklist for AI-made images.
YouTube upload bitrate: 8 Mbps at 1080p vs a 1080x1920 Short
YouTube recommends 8 Mbps for 1080p SDR (12 Mbps high frame rate). A 3-minute Short at 8 Mbps is about 180 MB. Sume trim conforms fps to 24, 25, 30 or 60.
YouTube SDR uploads: BT.709 and what to check on a Sume MP4
YouTube recommends BT.709 for SDR, 4:2:0, progressive, moov atom up front. Sume trim exact re-encodes libx264 yuv420p; check color tags with ffprobe.
H3 Max Recast: 1-4 person photos, 768p default, 1080p opt-in
H3 Max Recast swaps the people in one 5-30 s video using 1-4 reference photos, one per new person. Output is 768p by default; 1080p is opt-in.
Kling Motion Control prompt: appearance only, motion is the video
On Sume's Kling 3.0 Motion Control the prompt guides appearance only. Motion comes from motion_video_url, and the body rejects reference_image_urls and model.
Fit TTS audio to the 5 to 14.8 second H3 Max lip-sync window
Sume's H3 Max lip-sync accepts audio of 5 to 14.8 seconds and never clamps. Plan scripts of about 63 to 197 characters, and send anything else to Fabric.
Amazon Sponsored Brands video audio: PCM, AAC or MP3, and Sume
Amazon Sponsored Brands video takes PCM, AAC or MP3 audio, 16:9 only, 6-45 s. Sume's audio-detach gives wav pcm_s16le or 128 kbps mp3; a Sume MP4 needs a probe.
Pinterest video ads take H.264 or H.265: do you need H.265?
Pinterest video ads accept H.264 or H.265 in MP4, MOV or M4V, so an H.264 clip is fine. Sume's exact trim uses libx264; confirm any other output with a probe.