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
Timeline defaults to 1080x1920: join 16:9 AI clips without a crop
Timeline 1.0 renders 1080 by 1920 by default and fits slots with cover. For 16:9 Seedance, Wan or H3 clips, set output width and height and fit.
Captions that match your voiceover script: script_text on Sume
Burned-in captions can follow your script instead of the speech-to-text guess. Sume's script_text aligns to STT timing; here are its failure codes and limits.
Dailymotion accepts MP4 only: 1080p at 30 fps wants about 4.5 Mbps
Dailymotion accepts MP4 only and publishes bitrates per size, such as 1080p at 30 fps at 4.5 Mbps and 9:16 720x1280 at 2 Mbps. Render a match with Sume.
Facebook catalog image_link: 500x500, 8 MB, JPEG or PNG
Meta's catalog image_link must be at least 500x500, at most 8 MB, JPEG or PNG. Ask Sume for a 1:1 JPEG and measure the file before you add it to a feed.
Flickr video limits: 1 GB, 1080p, 3 free playback minutes
Flickr videos can be up to 1 GB at 1080p. Free accounts play the first 3 minutes and Pro plays 10, capped at 30 fps. Render a fitting clip with Sume.
GIPHY Clips specs: 30 seconds, 9:16 to 16:9, 100 MB, 24 or 30 fps
GIPHY Clips are 30 seconds or less, between 9:16 and 16:9, up to 100 MB at 24 or 30 fps, with sound and no black bars. Render one with Sume.
Reuse a social video as a YouTube ad: probe the file first
Google says social assets can run as YouTube ads if they meet specs. Probe the clip with Sume's unbilled video-inspect, then trim it if it is too long.
Instacart 3200x800 and 3200x400 banners: what Sume can make
Instacart banners are 3200x800 (4:1) and 3200x400 (8:1). Sume lists 4:1 and 8:1 ratios but no exact-pixel size in v1, so the final crop is yours.
Instacart lifestyle image: 1600x896 passes the 1067x600-1600x900 box
Instacart display ads take a 16:9 lifestyle image of 1067x600 to 1600x900, 1 MB max. Sume's custom size needs multiples of 16, so ask for 1600x896.
Instacart video thumbnail 1067x600 to 1600x900 from a clip
Instacart wants a 16:9 JPG or PNG thumbnail of 1067x600 to 1600x900, 10 MB max. Pull a still from your video with the unbilled video-frames route.
Kickstarter video: 5120 MB main video, optional 9:16 clip
Kickstarter's main video can be up to 5120 MB, and its optional Discovery Mode video is 9:16 vertical, 60 to 90 seconds. Render the vertical clip with Sume.
Lyric video captions for an AI song: pass the lyrics as script_text
Lyria 3.5 returns lyrics with the audio. Sume's captions API can take them as script_text to caption a video that carries the song. Steps and limits.
Microsoft Advertising image max 2592x2048: send JPEG, not PNG
Microsoft accepts GIF, JPEG and PNG up to 2592x2048 but converts PNG to JPEG and drops animation. Request jpeg from Sume and skip a lossy surprise.
Microsoft Advertising image sizes: 703x368, 1:1 and 4:1 from AI
Microsoft's Image object has six subtypes from 4:1 to 16:9. Sume cannot set exact pixels, so request the ratio, then crop each subtype to its minimum.
Nano Banana transparent background: no alpha option, use RMBG
Google's Gemini image docs do not list a transparency option, and Sume's background parameter is for GPT Image 2.5. Cut Nano Banana output out with RMBG 1.0.
Nextdoor video ad specs: MP4 or MOV, 500 MB, 2 to 300 seconds
Nextdoor video ads are MOV or MP4 up to 500 MB, 2 to 300 seconds, in 16:9 or 1:1 for the Newsfeed. How to render a fitting clip with Sume.
Paramount ad specs: :15 or :30 spots, 720p minimum, 6 Mbps
Paramount video ads are :15 or :30 spots at 1280x720 or larger, MP4 or MOV, 6 Mbps minimum, with 23.98 to 30 fps. What Sume can render for those.
Patreon native video: 720p/1080p, 100 hours a month, 10 min on iOS
Patreon native video uploads at 720p or 1080p, viewers default to 720p, and creators get 100 hours of media a month. Render a 1080p file with Sume.
Pinterest's "AI modified" label: IPTC metadata and classifiers
Pinterest labels Pins "AI modified" using IPTC metadata plus classifiers and self-reports, and you can challenge it. How to prepare an image with Sume.
Quora video ad specs: 3 to 60 seconds, 16:9, 70 MB, 30 fps max
Quora video ads run 3 to 60 seconds in 16:9 MP4 or MOV, 70 MB or less, H.264, 30 fps or less, 1280x720 recommended. How to render one with Sume.
Rumble ads video creative specs: 16:9 or 4:3, H.264 MP4, under 50 MB
Rumble video ad creatives must be 16:9 or 4:3, H.264 MP4 only, and under 50 MB each. How to render a 16:9 or 4:3 MP4 with Sume.
Snapchat Spotlight no longer recommends wholly AI-generated videos
Snap says wholly AI-generated videos are not eligible for Spotlight recommendation from July 31, 2026. What that means for clips you assemble with Sume.
Substack video upload: 1080p H.264 at 8 Mbps or below
Substack's fastest-processing tips are 1080p or 1440p or smaller, H.264, 8 Mbps or below, 5 to 120 fps and AAC. What Sume can render for it.
Suno's EQ and compressor tips vs Sume Timeline mix controls
Suno published guides on EQ and compression for AI tracks. Sume Timeline has gain and ducking but no EQ or compressor. What you can and cannot do.
Teachable video files: MP4, MOV or AVI, 2 GB each, 1080p
Teachable recommends MP4, MOV or AVI, 1080p at 24 to 30 fps, with 2 GB per file and 20 GB overall. How to render a fitting lesson with Sume.
Thinkific video upload: 3 GB, H.264 MP4, 5,000 to 8,000 kbps
Thinkific takes videos under 3 GB, H.264 MP4 at 5,000 to 8,000 kbps, constant 15 to 60 fps, up to 1080p. What Sume can render for it.
Topaz Starlight Fast 3 vs Sume Video Upscale: what you can set
Topaz says Starlight Fast 3 runs at 4x the speed of Precise. Sume Video Upscale 1.0 has its own fast, standard and pro tiers, priced per input second.
Udemy video standards: 720p or higher, 16:9, 30 minutes minimum
Udemy needs at least 30 minutes of video to publish a course, HD at 720p or higher, horizontal 16:9. Static slides count as low quality. Render with Sume.
Vidyard upload: raw files up to 20 GB, H.264 up to 4K
Vidyard accepts raw video up to 20 GB, then encodes H.264 MP4 derivatives from 360p to 2160p with AAC audio. What to render with Sume.
Vimeo upload settings: H.264, 10-20 Mbps at 1080p, constant frame rate
Vimeo recommends H.264 High Profile, 10 to 20 Mbps at 1080p, constant frame rate and AAC-LC audio. What Sume can and cannot set for you.
Wistia export: H.264 MP4 at 5,000 to 8,000 kbps, 26 GB cap
Wistia accepts files up to 26 GB and recommends H.264 MP4, 5,000 to 8,000 kbps, constant 15 to 60 fps, AAC audio. What Sume can render for it.
Yelp video ads: 2 minutes, 500 MB, and you upload the actual file
Yelp video ads allow up to 2 minutes and 500 MB in MP4, WMV, MOV or AVI, and YouTube or streaming links do not work. Render and trim a file with Sume.
YouTube image posts in Shorts: up to 10 images, 16 MB each, 1:1
YouTube image posts take JPG, PNG, GIF or WEBP up to 16 MB, up to 10 images per post, with 1:1 suggested. How to make 1:1 images with Sume.
Lyria 3.5 outputs MP3 or WAV: what you get from Sume music
Google lists MP3 by default or WAV for Lyria 3.5. Sume's music request has no format field and returns an audio file; timeline audio can make a wav.
Extract audio from a 30-minute video: the 900-second cap
Audio detach accepts a source up to 1800 seconds but returns at most 900 seconds of audio per job. Use range to split a 30-minute video into two detaches.
Extract audio from a video URL: why example.com is refused
Audio detach only reads a video already on this workspace's media.sume.com. An outside URL fails unsupported_media_source, so import it first, then detach.
ffmpeg -vn -ac 1 -ar 16000 as audio detach API fields
Audio detach rejects raw ffmpeg fields such as af, filter, cmd and codec. Map -ac, -ar and -ss/-to to channels, sample_rate and range; mp3 is 128 kbps.
Combine more than 20 audio files: nest the concat jobs
Timeline audio concat takes 1 to 20 parts per job. For 45 files, concat in batches of 20 or fewer, then concat the batch outputs. Four jobs, $0.04 flat.
Start a video's audio 45 seconds into a song: audio.source_in
Timeline 1.0's audio.source_in sets the in-point into a single audio spine. Output length stays duration_seconds, and it is illegal with parts or silence mode.
Timeline audio segments: re-base video start times after concat
After a concat, use segments[] (index, start, duration_seconds) as the on-spine start of each video slot in Timeline 1.0. Declared starts are authoritative.
audio_parts_channel_mismatch: concat needs one channel layout
Timeline audio concat fails with audio_parts_channel_mismatch when parts mix channel layouts. Detach video audio as mono for every part.
audio_parts_shorter_than_duration: fix a Timeline audio spine
Timeline 1.0 refuses audio.parts[] whose declared lengths sum to less than audio.duration_seconds. Add part length, lower the duration, or use silence mode.
Podcast transcription from the episode URL: parts and cost
Podcast transcription by API can read the episode's public audio URL, but only 10 minutes per request: longer episodes go in parts, at a per-minute rate.
Etsy listing video size: length, resolution, and file limits
Etsy listing videos run 3 to 15 seconds, up to 100 MB, and play without sound; Etsy calls 1080 px ideal. The rules, and making a clip from a photo.
Bulk add a watermark to videos: same logo, every file
To bulk add a watermark to videos, run one overlay job per video with the same logo and layout. How to keep it identical by API, and what it costs.
Captions vs subtitles: what's the difference?
Captions write down what is heard, sound cues included, for viewers who can't hear. Subtitles translate the dialogue for viewers who don't speak it.
How to sync subtitles with video: offset, drift, re-time
Sync subtitles by shifting every timestamp when all lines are off by the same amount, or scaling them when the gap grows. How to fix both for good.
How to make a video montage: clips cut to one music track
To make a video montage, pick the music first, mark where the cuts go, then lay short clips over the track at those times in one render.