Blog
Sume blog: agent-native video generation, Avatar 1.0 orchestration, and production APIs for builders and coding agents.
PHP: submit a 30-second Wan 3.0 clip, poll it, save the MP4
Plain PHP 8 with curl and no SDK: send a 30-second wan-3.0 request, poll the job, and write the MP4 to disk. The 720p run is reserved at $3.75.
A 3-minute YouTube Short from Omni clips: 18 takes, what it costs
YouTube says Shorts can run three minutes. At the 10-second Omni Flash cap that is 18 clips: the 720p and 1080p totals on Sume plus the Timeline join.
video-inspect vs video-frames: which returns the still you need
Video inspect gives a probe, 8 default stills at 768 px and optional STT for clips up to 1800 s; video frames gives exact stills at source size up to 300 s.
Edit a photo with Nano Banana: aspect_ratio auto and the cost of 100
Send a product photo as input_references to Nano Banana 2.1 or Pro and set aspect_ratio auto to keep its shape. Python request and cost of 100 edits.
Which ready-made Sume Formats can I call today? 27 slugs
Sume's first-party Format catalog answers at the sume handle with 27 slugs, from UGC and product demos to try-on, product splashes and recreate. List and call.
Omni Flash API errors: which to retry and which to fix
A retry policy for Gemini Omni Flash 1.1 calls on Sume: 400, 401, 402, 409, 429 rate_limited, 429 queue_full and 503 each mapped to retry, wait or fix.
Seedance reference inputs on Sume: images, video, audio per docs
Which reference types the Seedance ids accept on /v1/videos (images, video, audio, first and last frame), how references are priced, and a working request.
Which Sume video models stop at 15 seconds and which reach 30?
Seedance 2.5, Wan 3.0, Genjutsu and H3 Max Recast go past 15 seconds on Sume; MiniMax H3 stops at 15 and Gemini Omni Flash 1.1 at 10. The full limit table.
Notes on a reference ad: by hand vs one reference-ingest call
What you would log by hand while watching a reference ad, and the manifest Sume's reference ingest returns instead: shots, OCR, audio facts, strip.
Swift: URLSession async/await for one 30-second Wan 3.0 job
A 28-line main.swift that submits wan-3.0 for 30 seconds, polls with Task.sleep and saves the MP4. Runs on macOS or Linux with swiftc.
Kubernetes CronJob that submits a nightly 30-second Wan 3.0 clip
A CronJob manifest using curlimages/curl and a Secret: one dated Idempotency-Key per night, concurrency forbidden, and a month of reserves at each resolution.
What an agent should log when it calls Sume: ids yes, signed URLs no
Safe log fields for agents using the Sume API, CLI and MCP: request ids, job ids, status, sanitized media metadata. Never keys, signed URLs or transcripts.
Rotate the Sume webhook secret without dropping events
After POST /v1/webhooks/signing-secret/rotate, Sume signs with both secrets for 24 hours. How verifyWebhook handles the two-entry header, and the deploy order.
Review a 30-second Wan 3.0 clip: video inspect caps at 24 stills
Video inspect returns at most 24 stills per call, so a 30-second clip needs a sample rate of 0.8 fps or an explicit list of 24 times. Python builds the request.
PowerShell: Invoke-RestMethod for a 30-second Wan 3.0 clip
Windows PowerShell script that posts a 30-second wan-3.0 job, loops until it completes and saves the MP4 with Invoke-WebRequest. $3.75 at 720p.
Free, Pro, Startup, Scale: processing seats, queue slots, full hold
Sume's concurrency by plan, queue capacity max(3, 5 x concurrency), accepted job capacity, and the balance reserved if every slot holds a 10 s clip.
A first-frame still plus a 30-second Wan 3.0 clip: the pair's cost
Generate the opening frame with Higgsfield Soul, Seedream 5 Lite or Nano Banana 2.1, then animate it for 30 seconds on Wan 3.0. Totals at 480p to 1080p.
Own agent loop vs one Sume Agent Completion request
POST /v1/agent/completions runs the Sume Agent with tools and media generation in one async call: required spend cap, 30 images, a schema and a receipt.
When Seedance 2 Mini or Fast is enough, and when to pay for 2.5
A decision guide for Seedance tiers on Sume: what Mini, Fast and 2.5 cost for the same clip, what only 2.5 can do, and which jobs belong on which tier.
Five requests Omni Flash cannot take, and what to send instead
Gemini Omni Flash 1.1 on Sume refuses clips over 10 seconds, silent clips, audio references, 1:1 and 2K or 480p output. What to send instead for each.
Swap four people in one video: H3 Max Recast bills per second
h3-max-recast takes one source video and 1 to 4 person photos, 5 to 30 seconds. Price is $0.375 or $0.5625 a second whether you swap one person or four.
A three-stage video funnel: Grok, MiniMax H3, Seedance 2.5 costs
Screen 20 ideas on Grok Imagine, keep 5 for MiniMax H3 at 768p, finish 1 on Seedance 2.5 at 1080p. All 5-second clips: the funnel costs about $10.23 on Sume.
Sume TypeScript SDK waitForJob: 20-minute timeout, job keeps billing
How @sume-com/sdk waitForJob polls a generation job, what SumeJobTimeoutError means, and why a client timeout does not cancel or refund the job.
Trim before crop: how the 300 s filter limit sets the order
Video filter accepts sources up to 300 seconds while video trim accepts 1800. For a 20-minute clip, trim first, then crop: two jobs, $0.04.
Upscale old footage past 30 seconds: chunk, upscale, reassemble
Sume video upscale takes up to 30 seconds per call at $0.009 per input second. Chunk a 5-minute tape with video-trim, upscale each piece and join with Timeline.
Seedance output pixel sizes: 480p, 720p and 1080p for every ratio
The frame size Seedance renders at 480p, 720p and 1080p for 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16 on Sume, as used for pricing.
Python: submit, poll and download one Omni Flash clip (v1/videos)
A short Python script that submits a Gemini Omni Flash 1.1 request to Sume's /v1/videos, polls the job until it completes and saves the MP4.
Gemini Omni Flash 1.1 on Sume: spec sheet and billing in one page
Everything that ships for gemini-omni-flash-1.1 on Sume: 3 to 10 seconds, four resolutions, two ratios, always-on audio, reference limits, edit mode, billing.
sume/music-auto or pinned lyria-3.5: what changes in the job
Music Router takes sume/music-auto (Lyria 3.5 today), lyria-3.5 or lyria-3-pro. What job.model and routed_model echo back, and why the price stays the same.
Crop a 21:9 or 2.39:1 film clip to 9:16 with video filter
Width fractions for cropping ultrawide 21:9, 2.39:1 and 32:9 clips to 9:16 with one Sume video-filter crop op, plus the 0.05 minimum side and a free check.
Omni vs Seedance 2.5 vs Wan 3.0 for an 8-second sound-on ad
Price, length range and audio handling for an 8-second ad on Gemini Omni Flash 1.1, Seedance 2.5 and Wan 3.0 through Sume, with a pick-by-job rule.
detach_source_has_no_audio: check probe.has_audio first
Audio detach fails with detach_source_has_no_audio on silent video. Probe has_audio with a free frames-false video inspect first. Refusal codes listed.
One wrong sentence in an avatar script: what 5 re-renders cost
Changing a script means a new Avatar 1.0 job. Five full re-renders of a 20-second take cost $18.40 on standard, $24.50 on plus and $55.00 on max.
Poll /v1/jobs/{id}/status, then /result, in Node with backoff
A 25-line Node function that polls a Sume job on its own next_poll_after_seconds, reads /result only when the job completed, and keeps the id on timeout.
First-frame image for /v1/videos: public HTTPS only, no signed URLs
Image and video inputs to Sume generation must be fetchable public HTTPS URLs. Localhost, private IPs, signed URLs and wrong content types are rejected.
Higgsfield Soul on Sume: half a cent per image, batches of 1 or 4
higgsfield-soul costs $0.005 at 720p and $0.0075 at 1080p on Sume. It takes batch sizes 1 or 4, no references. Price table and a four-image call.
Does Seedance aspect ratio change the price? 21:9 vs 9:16 on Sume
Aspect ratio barely moves Seedance prices on Sume: 9:16, 16:9 and 1:1 cost the same and 21:9 or 4:3 add under a percent. The 720p table and the pixel sizes.
OpusClip Pro MCP connector vs the Sume hosted MCP: what differs
OpusClip lists a Video Editing API, Scheduler API and MCP connector on Pro. Sume has a hosted MCP with trim and inspect tools. What each gives an agent.
VEED green screen API per 30 frames: Sume has no video matting
VEED prices Green Screen at $0.025 per 30 frames. Sume does not remove video backgrounds; its filter route only dims, crops and applies ffmpeg filters.
Sonix Core, Advanced, Pro: the real hourly rate vs Sume
Sonix plans work out to $5.00, $2.50 and $2.00 an hour once you use every hour. Sume's transcript line is $0.60 an hour. When does a plan beat pay as you go?
Deepgram Flux TTS: text_spoken and barge-in vs Sume voiceover jobs
Deepgram's Flux TTS reports text_spoken and text_remaining when a caller interrupts. Sume has no barge-in, but word timestamps can mark a cut point.
Speech-to-speech vs cascade: does 42% lower latency matter for video?
A newsletter reports speech-to-speech models run 42% lower latency than cascades. Why that helps live agents, not a narrated video, and what to measure.
Voice API cost gap up to 213x: what drives it, how to price yours
Krisp's newsletter reports a voice API cost gap of up to 213x across OpenAI, Gemini and Qwen. Why list TTS prices differ far less, and how to normalise yours.
Qwen-Audio 3.1 price cuts: rebuild your voice bill with three numbers
Qwen-Audio 3.1 cut prices about 70% for TTS, 85% for Realtime and up to 95% for ASR. How to recompute your bill, and where Sume TTS and STT sit.
Amazon video ad frame rate: set Sume Timeline fps to 24, 25 or 30
Amazon lists 24, 25 and 30 fps among its rates. Sume Timeline takes 24, 25, 30 or 60. Choose a rate that matches the source to avoid the resample warning.
LinkedIn video ads need under 30 fps: render at 24 or 25 on Sume
LinkedIn's spec says frame rate must be less than 30 fps. Sume Timeline and trim accept 24, 25, 30 or 60, so only 24 and 25 fit. How to set it and check it.
Amazon lists 3840x2160, but Sume output tops out at 2160: what to do
Amazon Sponsored Brands video allows 3840x2160. Sume Timeline sides cap at 2160, so a 4K UHD frame is out. Here is the 1920x1080 route and what you give up.
Amazon Sponsored Brands video is 16:9 only: render 1920x1080 on Sume
Amazon lists 16:9 as the only aspect ratio for Sponsored Brands video. Set Timeline output to 1920x1080 at 24 fps and check the plan for free before you pay.