Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
App Store screenshot has an alpha channel: request jpeg
App Store Connect says screenshots can't include alpha channels or transparencies. Ask the Sume image API for output_format jpeg instead of png.
sync-3 image formats JPEG PNG WebP vs Sume image URL rules
sync-3 accepts JPEG, PNG and WebP stills. Sume's docs set URL rules instead: a fetchable public HTTPS image, with private and signed URLs rejected.
Sync Labs concurrent jobs per plan vs Sume plan-only concurrency
Sync Labs allows 1, 3 or 6 jobs at a time on Hobbyist, Creator and Growth and 429s past that. Sume queues jobs, and only the plan sets processing concurrency.
Sync Labs API rate limit: 100 per minute, and Sume headers
Sync Labs allows 100 POST /v2/generate and 600 GETs a minute. Sume has a per-plan requests-per-minute budget; read ratelimit headers and retry-after.
Sync Labs max video length by plan vs Sume avatar video limit
Sync Labs caps video at 1, 5 or 10 minutes on its lower plans. A Sume avatar video job covers 4 to 60 seconds; split longer scripts into several jobs.
Sync Labs pricing per second, and a Sume dry_run cost preview
Sync Labs bills per second on top of a $5, $19 or $49 plan, and lists sync-3 at $0.107 to $0.133 per second. On Sume, preview a paid call with dry_run first.
Synthesia dub speaker attribution vs Sume speech-to-text and audio
Synthesia lets Enterprise users reassign and rename speakers in a dub. Sume gives you audio detach, speech-to-text and audio joins; speaker mapping is yours.
Synthesia brand kit fonts vs Sume caption fonts: Hangul only
Synthesia Motion Graphics now use brand kit fonts. Sume's caption font field takes a Hangul face only, so Latin brand fonts cannot be set there.
Synthesia Layouts (100+ designs) vs Sume compose: stack or overlay
Synthesia Layouts ship 100+ scene designs in its editor. Sume compose builds one shot from one still and one video as stack or overlay. What to pick.
Tavus PAL MCP connectors vs Sume hosted MCP tools and gates
Tavus MCP connectors let a PAL call third-party MCP servers. Here is what Sume's hosted MCP at mcp.sume.com exposes and the gates a paid call needs.
Threads podcast guest card: pull the guest still with video frames
Threads now supports guest card posts for podcasts. To get the guest image from your episode video, ask Sume video frames for stills at the seconds you name.
Threads podcast video highlight: cut the clip with video trim
Threads now lets podcasters share highlights as video posts. Cut one standout moment from a long episode into a new MP4 with Sume video trim at $0.02 per job.
Threads podcast transcript post: burn the quote onto the clip
For a podcast quote clip, burn captions from your exact transcript text with Sume video captions script_text, or authored cues. SRT uploads are not accepted.
AI Gateway async video 413 at 300 KiB: hosted URLs on Sume
AI Gateway caps the persisted video start request at 300 KiB and answers inline base64 with 413. On Sume, send public HTTPS URLs; 413 is payload_too_large.
Vercel AI Gateway poll intervalMs and timeoutMs vs Sume polling
AI Gateway's poll option sets intervalMs (5000) and timeoutMs (600000). Sume jobs return next_poll_after_seconds, and your client owns the deadline.
AI Gateway startVideo webhookUrl: the same pattern on Sume
experimental_startVideo returns once the job is accepted and can call a webhookUrl. On Sume, send mode webhook with webhook_url and keep polling as backup.
Vidu Q2 Pro Fast image-to-video 1080p vs Sume first frame
QwenCloud lists vidu/viduq2-pro-fast_img2video at 720P and 1080P. Sume has no Vidu id; send image_url as the first frame to a 1080p model.
Vidu Q3 ad reference-to-video vs Sume reference images
QwenCloud lists a Vidu Q3 ad reference-to-video model. Vidu is not in Sume's video ids; reference images work on models that list them.
Vidu Q3 drama character consistency vs Sume reference images
QwenCloud lists Vidu Q3 drama for character consistency. Vidu is not in Sume's ids; on Sume, references guide a clip, and frame_images win if both are sent.
Vimeo pixel aspect ratio 1:1: setsar in a video filter
Vimeo recommends square pixels (1:1). Sume's video filter allowlist includes setsar, setdar and scale, so a filtergraph can set the sample aspect ratio.
VS Code 1.140 session authorization server: what Sume issues
VS Code 1.140 proposes a field naming the authorization server behind a session. For Sume, that server is the MCP origin, mcp.sume.com.
Wan 3.0 Prime vs Wan 3.0: one wan-3.0 id on Sume
QwenCloud and Runway list Wan 3.0 and a Prime variant. Sume's catalog lists one id, wan-3.0, with 2-30 s clips. Check the catalog for limits.
Wan 3.0 is public after invite-only: check Sume's wan-3.0 id
QwenCloud says Wan 3.0 went from invite-only on August 6 to public. On Sume, wan-3.0 is a catalog id; check the live catalog for limits.
Wan 3.0 smart duration and adaptive ratio vs Sume's explicit fields
QwenCloud lists smart duration and adaptive aspect ratio for Wan 3.0. On Sume you send an integer duration and an aspect_ratio the model supports.
Wan 3.0 sound toggle vs Sume generate_audio for Wan
Wan 3.0 lists a sound toggle at QwenCloud. On Sume, generate_audio defaults to the model's audio capability and some models reject false.
Apple Watch Ultra 4 screenshot size: 422x514 from Sume
Apple Watch Ultra 4 screenshots are 422 x 514 pixels. Sume's image API cannot output that size, but a Timeline still plus a PNG frame can.
Wix Video minimum size 480x470: crop and scale with video filter
Wix Video accepts 480x470 to 1920x1080. Sume video-filter crops by fractions and runs scale or pad in a filtergraph, with a free check before the encode.
Wix video poster 1944x2880: stills from a clip with video frames
Wix lists a video poster at 1944 x 2880 px. Sume video-frames makes JPG or PNG stills from a clip, but max_edge stops at 2160, so it cannot upscale to 2880.
Wix Video trailer size: cut a short trailer with video trim
Wix lists trailers at up to 100 MB. Sume video trim cuts an exact-length clip with duration and output width, height and fps. It has no file-size setting.
YouTube 48fps upload: keep the frame rate, conform to 24/25/30/60
YouTube accepts 48 and 50 fps and says to upload at the recorded rate. Sume's trim and Timeline output.fps conform only to 24, 25, 30 or 60.
YouTube: AI podcast hosts giving financial advice and monetizing
YouTube lists AI-generated podcast hosts offering financial guidance, investment tips or wealth management advice as not allowed to monetize.
YouTube AI persona policy: the AI doctor example
YouTube says channels using AI personas as human experts on health, legal, finance or politics cannot monetize. An AI doctor is its first example.
YouTube AI persona policy: legal advice and politics
YouTube's AI persona rule covers health, legal issues, finances or politics; AI personas giving legal advice or interpreting laws are a listed example.
Deinterlace before YouTube upload: Sume has no deinterlace filter
YouTube says deinterlace 1080i60 to 1080p30 before upload. Sume's video-filter allowlist names no deinterlacer and refuses unknown filters.
YouTube dynamic brand segments: make the segment clip
YouTube is testing brand segments inserted into up to 20 long-form videos. Make one clip, then trim and assemble variants of it with Sume Timeline.
YouTube first-frame views: check your opening frame at t=0
YouTube now counts a view from the first frame, including autoplay and hover. Pull frames at 0, 0.5 and 1 s with Sume video frames to see what plays first.
YouTube moov atom and edit lists: keyframe trim vs exact trim
YouTube asks for MP4 with moov first and no edit lists. Sume's keyframe trim is a stream copy; exact re-encodes. The docs do not state moov placement.
YouTube Opus and Eclipsa Audio uploads vs Sume's WAV and MP3
YouTube now lists Opus and Eclipsa Audio beside AAC-LC for uploads. Sume audio outputs are wav (pcm_s16le) and mp3 only; neither is Opus or Eclipsa.
YouTube 1080p bitrate: 8 Mbps, and Sume has no bitrate field
YouTube recommends 8 Mbps for 1080p SDR at 24 to 30 fps and 12 Mbps at 48 to 60. Sume rejects codec and crf fields and exposes no bitrate setting.
YouTube upload H.264 settings: what Sume's exact trim sets
YouTube lists H.264 High Profile, 4:2:0 and progressive scan. Sume's exact trim re-encodes with libx264 and yuv420p; profile, GOP and CABAC are not fields.
One video ad into many variants with the same pacing, by API
Send one source ad to Sume's video edit once per variant, each with a single-change prompt ending 'Keep everything else the same.' One job and one key each.
Add film grain to a video by API with the noise filter
Add film grain to a finished clip with the allowlisted noise filter in Sume's video filter: one encode job, a new MP4, and a free check before you pay.
Add motion blur to video: the tmix frame-blend filter API
Sume's video filter has no motion-blur filter, but tmix and tblend blend neighboring frames for a blur-like trail. Limits on a 24 fps source, and the check.
Add a vignette to a video by API with the vignette filter
Add a lens-edge vignette to a Sume-hosted clip with the allowlisted vignette filter: one encode job, a new MP4, and limits on graph size and source length.
Apple Music ai_transparencies Artwork value for AI cover art
If AI generated a material portion of an album cover, Apple Music spec 5.3.26 asks you to add the Artwork value in ai_transparencies. Omitted means none.
Apple Music ai_transparency: Composition vs Track for AI songs
Apple Music spec 5.3.26 has Composition for AI lyrics or components and Track for an AI sound recording. A song from a prompt usually needs both values.
Akool talking photo links expire in 7 days: what to archive
Akool says talking photo image, video and voice resources are valid for 7 days, so save them early. Sume media URLs do not expire; archive by need.
ant apply agent file: declare the Sume server, keep the key out
In an ant apply agent file, declare the Sume server by name and URL, https://mcp.sume.com/mcp. The API key belongs in a vault, never in the committed file.