Blog
Sume blog: agent-native video generation, Avatar 1.0 orchestration, and production APIs for builders and coding agents.

Festival lineup reel at 9:16: Seedance 2.5, 12 s, audio reference
A 12-second vertical lineup teaser with a track from the festival costs $6.94 at 720p on Sume with Seedance 2.5. Reference audio adds no surcharge.

Nano Banana 2.1 PDF and video grounding: Sume takes image URLs
fal's Nano Banana 2.1 Edit page lists video and PDF grounding. Sume's Image API takes public HTTPS image URLs only, so render pages first.

Next.js 16.4 Cache Components: will a Sume webhook route break?
Next.js 16.4 turns on Cache Components in create-next-app. A POST route handler is never cached, so a Sume webhook route works if it reads the raw body.

Next.js 16.4 GET route handler: poll a Sume job at request time
With Cache Components, Next.js 16.4 runs GET handlers at request time. A Sume job status route stays live if it sends no-store and follows the poll hint.

Nonprofit donation appeal: a 15-second video from two Omni clips
A 15-second appeal in 9:16 is two Omni clips, 10 and 5 seconds, joined on Sume. $1.875 at 720p for both. Where to put captions, and what the watermark means.

Replace videos.create_and_poll with a requests helper on Sume
The OpenAI Python SDK's create_and_poll and download_content have no Sume twin. Here is a 25-line requests helper with the same call shape and a safe retry key.

OpenRouter video client on Sume: swap the base URL, change webhooks
A client written for OpenRouter /videos works on Sume after you change the base URL, key and model ids. The webhook body and signature are different.

Pinterest video ad 4-second minimum: trim allows 0.2, so check
Pinterest video ads need 4 seconds minimum, 15 minutes maximum. Sume trim cuts from 0.2 seconds, so read duration_seconds on the result before you upload.

Pixel art and isometric video with Omni Flash: prompts
Prompt wording for pixel-art and isometric looks in Gemini Omni Flash, what Google's page says the model cannot control, and the cost of a draft on Sume.

Podcast teaser video: Omni cover-art clip plus your audio
Omni Flash makes its own sound and takes no audio upload. How to make a 9:16 podcast teaser on Sume: animate cover art for $1.00, then bring in your own audio.

Pointing the OpenAI SDK at api.sume.com: why Sora calls still fail
Changing only the base URL does not carry a Sora call to Sume. Five documented differences: model ids, body format, seconds and size, status words, download.

Polling Omni jobs can't 429 your submits on Sume
Sume gives each API key separate read and write budgets: 120 writes and 4,800 reads a minute on Free, 1,200 and 48,000 on Scale. The math for an Omni batch.

Qwen Image Max or Ideogram 4.5: 100 images, price and limits
100 images cost $9.375 on Qwen Image Max and $3.75, $7.50 or $27.50 on Ideogram 4.5 by quality. Ratios, references and output formats side by side on Sume.

Railway closes idle HTTP at 5 minutes: why Sume sync waits 30 s
Railway keeps a request open up to 15 minutes only while data moves. Sume sync mode caps the wait at 30 seconds, so long video jobs need async or a webhook.

Worker crashed mid-poll: list Sume jobs and join on idempotency_key
After a restart, GET /v1/jobs?status=processing lists your in-flight video jobs. Each row carries the idempotency_key you sent, so match your records on it.

Reconcile an overnight Sume Format batch: list runs, limit and cursor
List a Format's runs newest first with limit 1 to 100 and a cursor. There is no cross-Format list, so one call per Format. Curl loop to page through a batch.

Recraft V4 or ChatGPT Image 2.5 for marketing graphics on Sume
Recraft V4 bills $0.05, text-only, webp only. ChatGPT Image 2.5 bills by tokens, makes transparent PNGs and takes a mask. Which row for which job.

Same Omni video twice: no seed, but a replay returns it
Omni Flash lists no temperature or seed, and Sume rejects seed on every video model. To repeat a clip, replay an idempotency key or use a video_url edit.

SCORM export for AI avatar video: HeyGen, Colossyan, and Sume
HeyGen Business and Colossyan Professional list SCORM export. Plan prices, export limits and quizzes, and what Sume returns instead: a plain MP4 with no SCORM.

Shopify plays video at 480p to 1080p: what a 4K source costs on Sume
Shopify says streaming playback adjusts between 480p, 720p and 1080p though uploads reach 4K. A 10-second Omni clip is $1.88 at 1080p and $3.75 at 4K on Sume.

Shortest ad video: Pinterest 4 s, LinkedIn 3 s, Google action 10 s
Minimum video length per ad platform, read from each vendor page on 2026-10-08, against the 0.2 second floor of Sume video trim. One cut, one duration check.

Sora download_content vs Sume /content: the 302 and two 409 errors
OpenAI's content endpoint took variant=video, thumbnail or spritesheet. Sume's /content redirects with a 302 and returns two different 409s. How to branch.

Sora input_reference image: upload with uploadFile, use frame_images
OpenAI took the first-frame image as multipart input_reference. Sume wants an HTTPS URL: upload with the SDK's uploadFile, then pass it as frame_images.

Sora jobs in flight at shutdown: reconcile, then resubmit to Sume
OpenAI's page gives the removal date but not in-flight jobs. Mark every unfinished Sora row, then resubmit its prompt to Sume with a key built from the old id.

Measure your own render time on Sume from job event timestamps
No published Sora timing carries over. Read GET /v1/jobs/{id}/events, diff created, started and completed, and keep your own queue and render split per model.

Sora to Sume pull request review: eight lines to check before merge
A reviewer's checklist for a Sora-to-Sume PR: duration and resolution types, status words, the 302 download, the webhook body, idempotency and removed fields.

Sora API gone: port to Sume with Python urllib, no extra packages
Replace the OpenAI videos calls with a stdlib-only Python script: submit to Sume /v1/videos, poll, then fetch the 302 artifact URL without sending your key.

Speech-to-text for short voice notes: one request, sync mode
Send a voice note's public URL to Sume STT with mode sync and a 30-second wait. A cent per minute, plus the poll fallback when the job outlasts the wait.

Stop a Sume Format bulk run mid-batch: cancel starts the next item
The bulk API has no cancel-queue endpoint, and canceling a running child frees its slot for the next item. How to stop a runaway batch, and how to size queues.

Streamlit Sora demo: switch to Sume and st.video, no double billing
Streamlit reruns your script on every click. Derive the Sume Idempotency-Key from the prompt so a rerun returns the first job, then show the clip with st.video.

sume/auto and idempotent retries: same price, same route on replay
New video models land weekly. With model sume/auto and an Idempotency-Key, a retry of a Sume video submit gets the original job, price and route.

Cancel a Sume bulk run: no queue endpoint, so cancel each child
Sume has no public cancel for a bulk queue. Poll the queue, then POST /v1/format-runs/{run_id}/cancel for each running child. fal cancels one request with PUT.

Resume a bulk run after a crash: replay the Idempotency-Key
If your client dies after POSTing a 100-item bulk run, replay the same key and same body: Sume returns 202 with the original queue. A new body gets 409.

Wallet 402 or spend cap: which stops a Sume holiday batch first
A low wallet blocks a Format run at create with 402 insufficient_credits; a spend cap ends a running run as failed. Sizing a cap per item.

Sume Image API 400 unsupported_parameter: which field fails where
Which Sume image models list quality, resolution, mask_url, background, output_format and references, and which never do (seed, stream). Plus a check script.

result_ready vs terminal vs completed: gate the Sume result fetch
Poll a Sume job until terminal, fetch the result only when result_ready is true. Failed and canceled jobs answer 409 job_not_completed on /result.

Sume TTS word timestamps to caption cues for a narrated 60-second clip
Ask Sume TTS for timestamps.words, group them into cues and send them to video-captions so no recognition runs. About 25 cents for a 60-second narration.

Webhook endpoint down: redeliver a Sume video job after the retries
Sume retries a job webhook 10 times, 30 seconds apart. If your receiver was down longer, POST /v1/jobs/{id}/webhook/redeliver re-sends the terminal payload.

waitForJob times out at 20 minutes: why it does not fit a Vercel route
Sume SDK waitForJob waits 20 minutes by default and the job keeps billing if it throws. Vercel functions default to 300 s, so wait in a worker.

Sume wave_size_hint and a Worker subrequest limit: submit in waves
A Worker fan-out of Sume jobs hits 50 subrequests on Free. Size each wave from generation_limits, not from the hint alone, and stop at queue_capacity_remaining.

Synthesia's 60 free Interactive Avatar minutes: what they cover
Every Synthesia plan now includes 60 one-time Interactive Avatar minutes at signup. What that buys, what it does not, and the rendered-clip route on Sume.

Synthesia Creator is now Pro, same price. HeyGen has both names
Synthesia renamed Creator to Pro on October 1, 2026 with unchanged price and features. HeyGen still sells separate Creator and Pro plans. A name-by-name guide.

Synthesia dubbing with lip-sync: 80 credits a minute in dollars
Synthesia's plan article prices dubbing with lip-sync at 80 credits a minute. On the pricing page's plans that is about $0.85 to $1.86 per dubbed minute.

Synthesia Expert Sessions vs a Sume product walkthrough clip
Synthesia's Expert Sessions, announced as coming soon, let an avatar guide users step by step. A 30-second Sume product clip costs $5.82 to $17.40.

Synthesia Pro 2x to 8x: 12,000 to 48,000 credits vs Sume rates
Synthesia's new Pro 2x, 4x, 6x and 8x plans list 12,000 to 48,000 monthly credits. About 120 to 480 video minutes against Sume's $11.04 to $33 per minute.

Tavus 30-second minimum per conversation: what short calls cost
Tavus bills every conversation at least 30 seconds, so a 5-second call costs $0.185 at Starter overage. Plan math for short calls and Sume's 4-second floor.

Turn a roleplay debrief into an avatar feedback clip in Python
Take the written debrief from a roleplay or survey session and render it as a 16:9 Sume avatar clip with a retry-safe key, a 12 to 168 word check and polling.

Veo 3.1 clip older than 2 days: it cannot be extended
Veo 3.1 extends only Veo-made clips kept 2 days. If yours expired, here is what Google's page allows and what Sume's Omni edit and new generation do.