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
Children's captions at 17 characters per second: Netflix rule and Sume
Netflix's English style guide sets 20 chars per second for adults and 17 for children. See how to approximate it with Sume caption phrasing overrides.
Demand Gen video under 10 seconds: no in-stream; upload 1 to 5 videos
Demand Gen needs 5 seconds minimum, but videos under 10 seconds can't serve on YouTube in-stream. Upload 1 to 5 per ad; crop a 9:16 master on Sume.
Does a Google Ads video need YouTube first? Public or unlisted
Google Ads video ads need a YouTube upload first, public or unlisted. The help pages, two upload routes, and what a Sume MP4 must do before it is an ad.
Performance Max AI video: sourced, enhanced or auto-generated?
Performance Max has three AI video features: sourced (opt-in), enhancements (default on), auto-generated (when you upload none). Which one touches your clip.
SCC caption file: YouTube's preferred format vs Sume burn-in
YouTube calls .scc its preferred caption file format. Sume burns captions into the video and takes no SRT upload. When each one is right, plus a workflow.
Video reach campaign: which video lengths to cut from one master
A Google Ads video reach campaign wants a 15 s, a 6 s and sometimes a 30 s horizontal cut, plus a vertical one. Google's compositions, and trims on Sume.
YouTube in-feed video ad: vertical video and thumbnail size
Can a vertical video run as a YouTube in-feed ad, and what thumbnail size does Google list? Specs from Google Ads Help, plus a 1:1 crop and a still on Sume.
YouTube Pause ad specs: 1080-1350 px image, 2 MB, 70-char headline
YouTube Pause ads are static images shown 10 seconds after a pause on connected TVs. Google's creative specs, and how to make the image on Sume.
YouTube video blurry after upload? Wait for HD, then check the file
YouTube Help says HD and 4K take longer to process and Studio shows the estimate. Check the Sume file's size with video-inspect before you blame processing.
YouTube .vtt: positioning yes, styling only b/i/u. Sume design options
YouTube's .vtt support allows positioning but limits styling to bold, italic and underline. Sume burns richer styling; see which route fits your look.
Add subtitles to a video in DaVinci Resolve, or with a caption API
Resolve 21 transcribes and translates speech to text in the app. Sume video-captions burns styled captions into a public MP4 URL for $0.20 up to 60 seconds.
Descript AI music and sound effects vs generating music by API
Descript's 2026-09-17 update generates music and sound effects on request. Sume's Music Router generates music from a prompt; it has no sound-effect route.
Descript's ElevenLabs voice library vs Sume TTS voices
Descript's voice picker now uses the ElevenLabs voice library. Sume text-to-speech uses its own voices, and blocks a voice-language mismatch with a 409.
Descript scrubbing 2-5x faster vs a video-frames contact sheet
Descript's 2026-09-17 update speeds scrubbing with pre-computed video chunks. For a quick look at a file, Sume video-frames returns 1 to 24 stills.
FFmpeg 9.0.2 Lei: what is new, and what hosted trim exposes
FFmpeg 9.0.2 shipped 2026-09-18. Sume runs ffmpeg for you but accepts no ffmpeg flags: trim takes start, duration, precision, audio and output.
Final Cut Pro 12.4 Cinematic edits: export flat, then caption
Final Cut Pro 12.4 edits Cinematic focus after the fact. Sume reads a public MP4 URL, so export a flattened file first, then trim or caption it.
Firefly Video Editor Quick Cut vs a scripted first cut
Adobe's Firefly Video Editor has Quick Cut for a first cut from raw footage. Sume can inspect clips, trim, and join them on a timeline, but picks no shots.
OpenShot 4.0.1 Razor tool vs a hosted trim: exact or keyframe
OpenShot 4.0.1 upgrades its Razor cutting tool. Sume's video-trim cuts a clip by start and duration, exact (re-encode) or keyframe (stream copy), at $0.02.
Premiere 26.5 4:2:2 10-bit HEVC: probe a file before an exact trim
Premiere 26.5 decodes 4:2:2 10-bit HEVC MXF on NVIDIA Blackwell. An exact Sume trim writes libx264 yuv420p, so probe the source with video-inspect first.
Premiere 26.5 Generative Media Tool vs a video generation API
Premiere 26.5 adds a Generative Media Tool for video and sound effects. Sume's POST /v1/videos is the scriptable route, with frame_images for image-to-video.
Premiere 26.5 Match Source audio vs audio detach channels and rate
Premiere 26.5 can match source channel count and sample rate. Sume audio-detach sets channels and sample_rate: 16000 mono is the speech-to-text shape.
Premiere 26.5 Object Mask vs Sume background removal on stills
Premiere 26.5 adds Sharp and Smooth Object Mask modes for video. Sume's RMBG removes backgrounds from images only and returns a PNG with alpha.
Premiere 26.5 ProRes RAW and ARRICORE: send Sume a deliverable
Premiere 26.5 adds Sony FX5, ProRes RAW and ARRICORE support. Sume takes a public HTTPS video URL, so export a deliverable first, then probe it before spending.
Resolve 21.1 multicam up to 25 angles vs Sume timeline slots
Resolve 21.1 adds multicam viewing with shortcuts for up to 25 angles. Sume has no multicam; Timeline 1.0 stacks 1 to 200 clips on one audio spine.
Resolve 21 IntelliSearch vs a transcript with word times
Resolve 21 IntelliSearch finds moments in your footage. Sume's video-inspect returns a transcript with word times, which you can search for a trim point.
Resolve 21 Speech Generation vs a text-to-speech API call
Resolve 21 generates speech from text with Blackmagic voice models. Sume's tts_create does it from a script, and a voice-language mismatch returns 409 first.
Resolve 21 UltraSharpen and Motion Deblur vs an upscale API
Resolve 21 adds UltraSharpen and Motion Deblur. Sume's video upscale API takes 1 to 30 seconds, a 1.1 to 4 factor and a fast, standard or pro tier.
Caption a Recast video: burn captions after the person swap
Run h3-max-recast first, then send its output to POST /v1/video-captions. The kept source audio gives the captions speech to transcribe.
Cut a clean voice reference from video: audio detach range, mono wav
Sume's audio detach takes a start and end range and can output mono wav at 16 kHz. Cut 10 seconds of a single speaker for $0.01, then check it before use.
Does Recast change the background? Check frames with video inspect
Docs say Recast keeps motion, camera, cuts and sound, not props. Compare matching stills from source and output with POST /v1/video-inspect.
Open vs closed captions vs subtitles: what Sume's captions are
Sume's video captions are open captions burned into the pixels. The docs list no SRT or VTT export, and SRT uploads are unsupported. When that is right.
Pick a listing main image from a product clip with video-frames
Extract up to 24 stills from a product clip with POST /v1/video-frames on Sume, choose the sharpest one for a listing, and avoid the media.sume.com trap.
Sneaker on a foot photo, then a 9:16 clip: image edit plus Videos API
Put a sneaker product shot on a foot photo with gpt-image-2.5, then animate that still with a first_frame on POST /v1/videos. Two calls, one Sume key.
TikTok ad caption budgets: 100 in TopView, 150 for Spark Pull, 4 lines
TikTok's TopView page caps ad captions at 100 characters, Spark Pull allows 150, and both display four lines. Limits by placement and short burned-in text.
TikTok ad profile photo: 98x98, under 50 KB, logo in the 66px centre
TikTok in-feed ads use a 98x98 square profile photo under 50 KB, with key elements inside a 66px centre. Pull a brand still with Sume video frames and fit it.
TikTok ad safe zone shrinks with caption length: place burned-in text
TikTok says the ad safe zone changes with format and caption length. How to place burned-in captions inside it with Sume's caption anchor_ratio and frames.
TikTok effect music cover 800x800: generate 1024x1024, then resize
TikTok wants an 800x800 music cover with the brand in a 260px centre circle. 800x800 is below Sume's GPT pixel minimum, so render 1024 and resize.
TikTok branded effect music: 15 to 60 seconds, MP3 or WAV, from a clip
A TikTok branded effect official music track runs 15 seconds to one minute as MP3 or WAV. Pull that range from your own video with Sume audio detach.
TikTok Spark Ads: 10-minute cap on sparked videos, probe then trim
TikTok's Spark Ads page says videos over 10 minutes cannot be sparked, though the in-feed page says no duration limit. Probe the length, then trim.
Try-on still to a 6-second reveal: Gemini Omni start and end frame
Use gemini-omni-flash-1.1 with an image_url and end_image_url on Sume to animate a try-on from the plain product shot to the finished look.
Sale banner compose errors: not a still, wrong axis, clamped duration
Fix the stable Sume Timeline compose refusals for a sale banner: compose_image_not_still, compose_image_region_wrong_axis and a clamped duration warning.
Cyber Monday half-banner: price card over a clip, compose stack
Stack a Sume-hosted price card above a product clip in one vertical shot with Timeline compose, at a flat $0.02 per job, then drop it into a Timeline.
Fake a second camera on one AI clip: a punch-in cut for Shorts
Crop one AI clip with video-filter, then cut between wide and tight versions in Timeline 1.0 at the same moments, so a Short keeps moving without regenerating.
Gemini SynthID audio check: detach the track from a Sume video
Gemini's SynthID checker takes audio under 1 hour. Detach a Sume video's audio as wav or mp3 and see which format stays under 100 MB.
Gemini SynthID: 10 video checks a day, which clips to submit
Google's Gemini app allows about 10 video checks per 24 hours, up to 5 minutes in total. Work out how many clips fit and which ones are worth checking.
Gemini SynthID video check: 100 MB, under 90 seconds, trim first
Google's Gemini app checks videos for its SynthID watermark up to 100 MB and under 90 seconds. Trim a longer Sume video to fit, and know what a miss means.
Halloween teaser cut: Video trim start and duration, exact or keyframe
Cut a short Halloween teaser from a longer clip with Sume Video trim: start plus duration, frame-exact or keyframe copy, at a flat public rate per job.
Holiday sale instrumental on Music Router: length in the prompt
Generate an instrumental sale-reel track with Sume Music Router: duration fields are rejected, so state length and structure in the prompt.