Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
MAI-Voice-2.1 is public preview, no SLA: plan ad voiceover around it
Microsoft's MAI-Voice-2.1 doc says public preview, no SLA. What that means for a campaign deadline, and how to keep a fallback voice ready.
MAI-Voice-2.1 has 97 voices: en-US has 7, es-ES and en-AU have 1 each
Microsoft's MAI-Voice-2.1 doc lists 97 prebuilt voices over 28 locales. We counted per locale: some have seven choices, others only one.
Facebook feed video ad minimum is 120 px; Sume's smallest is 256
Meta's Facebook feed video spec lists 120 px minimum sides. Sume Timeline renders even sizes from 256 to 2160, so the floor never blocks an upload.
Gemini voice remixing is 'coming soon': what Sume TTS can change today
Google says Gemini voice remixing for timbre, pitch, pace and accent is coming soon. Sume TTS today has speed, volume and an emotion string only.
Luma Ray3.2 API: the docs page still lists ray-2 and ray-flash-2
Luma says the Ray3.2 API is live. The docs page I read on Oct 7 lists only ray-flash-2 and ray-2. How to check before you code, and Sume's gap.
20-second product video: Omni caps at 10 s, Wan 3.0 does it in one
A 20-second product video is one Wan 3.0 job on Sume: $2.50 at 720p, $5.00 at 1080p. Omni caps at 10 seconds, so 20 seconds means two clips and a join.
Gemini Omni Flash edit on Sume: a Python preflight for bad fields
A 29-line Python preflight for Sume video-router edit requests on gemini-omni-flash-1.1: catches the fields the docs say it rejects before you pay for a job.
Python CI guard: fail the build on retired Veo, Imagen, Sora ids
Twenty-three lines of standard-library Python scan a repo for Veo 2/3, Imagen 4 and sora-2 ids with their shutdown dates, and exit 1 when one is found.
MiniMax H3 outputs 24 fps and 32 kHz stereo: what Sume's H3 adds
MiniMax's H3 open-source post lists 24 fps video and 32 kHz stereo audio, 4 to 15 s clips and 768p by default. Sume's minimax-h3 takes 5 to 15 s.
Codex 0.160.0 MCP status for one server: confirm Sume with mcp_health
Codex 0.160.0 adds single-server MCP status discovery with thread connection reuse. Confirm the Sume session itself with mcp_health and tools_list.
Cursor project .cursor/mcp.json or global ~/.cursor/mcp.json for Sume?
Put a URL-only Sume entry in .cursor/mcp.json to share it with a repo, and keep any API key in an env variable in the global file, not in git.
Deno: time out a Sume video submit, then retry with the same key
A fetch that times out may still have created a job. A 20-line Deno submit retries only 408, 429, 5xx and timeouts, always with one Idempotency-Key.
Meta wants a fixed frame rate: set Timeline output.fps when clips mix
Meta's Facebook feed page requires a fixed frame rate. Sume Timeline takes output.fps 24, 25, 30 or 60, and mixed-rate sources are resampled with judder.
HappyHorse 1.1's five aspect ratios vs the Sume video catalog
HappyHorse 1.1 on Cloudflare takes 16:9, 9:16, 1:1, 4:3 and 3:4. Which Sume video models cover all five, and which do not.
Python guard: refuse a Short over 180 s before the render bills
A 20-line Python check that blocks a Shorts render over 180 seconds and prices the Sume Timeline minutes (10 cents each) before you submit.
Python urllib: honor retry-after on a Sume 429, back off without it
A stdlib retry for GET calls that sleeps for retry-after when the 429 carries it and for a capped exponential delay when it does not, with jitter.
Akool resolution 1080P to 16K by plan vs Sume Avatar video at 720p
Akool lists max resolution of 1080P on Starter, 4K on Pro, 8K on Pro Max and 16K on Business. Sume Avatar 1.0 talking video is 720p at this time.
Qwen Image 2.1 sizes (2752x1536, 2400x1792) vs Sume Qwen ratios
The Qwen-Image-2.1 card lists 2048x2048, 2400x1792 and 2752x1536. Sume qwen-image takes 13 aspect_ratio values instead of pixels. How they line up.
Check a reference image URL before sending it to Sume Images
Sume rejects localhost, private-network and non-HTTPS reference URLs before submission. A short Python pre-flight check that catches them first.
Akool max video length: 15 to 60 minutes by plan vs Sume's 60 s
Akool lists 15, 30, 45 and 60 minute maximum video lengths on its four paid plans. A Sume Avatar 1.0 job tops out at 60 seconds; here is the cost of the gap.
n8n 2.43.0: resume agents after waiting workflows, with Sume runs
n8n 2.43.0 (pre-release, Oct 6) resumes Preview agents after waiting workflows finish. Pair a long Sume run with one webhook, deduped on request_id.
Runway hailuo3 at 10-15 credits vs h3_max at 5-8, and Sume's H3 ids
Runway lists hailuo3 at 10 to 15 credits a second and h3_max at 5 to 8. Sume has minimax-h3 and minimax-h3-max at $0.0625 to $0.20 a second.
Does MiniMax H3 have an API? Three endpoints, or one route on Sume
Yes. MiniMax lists three Open Platform endpoints for H3: create, h3-context-ir and regeneration. Sume wraps H3 in one async video route, minimax-h3.
SynthID on every Gemini TTS clip: keep the original file for ad review
Google marks every Gemini 3.8 TTS clip with SynthID and C2PA credentials. What that means for ad voiceovers, and what Sume docs do and do not say.
Crop 21:9 to a 1:1 square: width 0.4286, centered x 0.2857
A 2520x1080 ultrawide clip becomes 1080x1080 with a crop of width 0.4286. TikTok's in-feed page lists 1:1 at a 640x640 minimum. Request and numbers inside.
Facebook feed ad text 50-150 characters, headline 27: what Sume burns
Meta's Facebook feed video page lists 50-150 characters of primary text and a 27-character headline. Sume's burned captions never touch those ad fields.
SQLite: add a sume_job_id column to rows that used sora-2 snapshots
OpenAI removed the Videos API and every sora-2 snapshot on Sept 24, 2026. A migration that tags old rows, then re-renders each once through Sume.
Runway Gen-4 Turbo at 5 credits a second: Sume's closest rates
Runway lists gen4_turbo at 5 credits a second, $0.05 at $0.01 a credit. Gen-4 Turbo is not on Sume; its cheapest video seconds start at $0.0375.
Wan 2.7 vs Wan 3.0: clip length and resolution limits by model id
Wan 2.7 tops out at 15 s and starts at 720P; Wan 3.0 reaches 30 s and adds 480P. Alibaba's ids side by side, and which one Sume lists.
Wan 3.0 API rate limit: 300 RPM on Model Studio vs Sume jobs
Alibaba lists 300 requests per minute for Wan 3.0 on Model Studio. Here is what that means for a batch, and how Sume submits Wan 3.0 as async jobs.
GPT Image 2.5 banner: 3840x1280 passes the 3:1 rule
3840x1280 is exactly 3:1, both edges are multiples of 16 and it is 4,915,200 pixels, so Sume accepts it on GPT Image 2.5. The four checks shown.
Crop a 720p 16:9 clip to 1:1: 720x720 clears TikTok's 640x640
A 1280x720 clip cropped with width 0.5625 gives 720x720, which clears TikTok's 640x640 square minimum with 80 px to spare. Request and numbers inside.
How many languages do AI avatar tools list? Six pricing pages
Creatify lists 75+, Captions 100+, Colossyan 120+, Synthesia 140+, HeyGen 175+ dialects. Sume's avatar docs give no language count. What to test instead.
YouTube lists 1440p at 16 Mbps; Sume Timeline cannot output 2560x1440
YouTube recommends 16 Mbps for 1440p SDR. Sume Timeline caps each edge at 2160, so 2560x1440 is not possible; the closest 16:9 render is 2160x1214.
Instagram feed video ad 1% ratio tolerance in pixels at 1080 wide
Meta lists a 1% aspect ratio tolerance for Instagram feed video ads. Read as relative, at 1080 wide that is about 1902-1938 px tall; Sume's 1080x1920 is exact.
"Keep the product identical": the Sume docs background-swap prompt
Sume docs use one prompt for a product edit: keep the product identical, swap the background. The request, the fields it needs, and what to check afterward.
Put your 16 strongest hooks first: Sume bulk queues start in order
A bulk queue returns 202 with the first `concurrency` items already running, up to 16. Order your 100 weekly ads so the best hooks are the first ones you see.
Bulk queue item error: format_run_canceled vs format_run_failed
In a Sume bulk queue, a failed child reads format_run_failed and a canceled child reads format_run_canceled. The real reason is in the child run receipt.
OpenRouter video client on Sume: six documented differences
Sume says /v1/videos matches the OpenRouter Video Generation API except six items: base path, auth, model ids, auto routing, size and provider.options.
Go httptest: a four-case table test for a Sume webhook handler
Sign a fixture body with sume-v1 HMAC, then assert 204 for a valid call and 401 for a stale timestamp, an empty server secret and a wrong secret.
TikTok horizontal ad minimum is 960x540: which 16:9 sizes clear it
TikTok's in-feed page lists 960 x 540 as the minimum for 16:9. Sume Timeline accepts 960x540, 1280x720 and 1920x1080, all at $0.10 per output minute.
Claude Code allowedMcpServers: the serverUrl rule for mcp.sume.com
Allow only Sume's hosted MCP endpoint in Claude Code managed settings with an allowedMcpServers serverUrl entry, and what the rule does not control.
Image API n: 10 per call in the schema, lower for each model
The Sume Image API schema allows n from 1 to 10, but each model lists its own n range. How to read the ceiling and what you pay for n images.
Which Sume video models take an audio_url reference, which do not
Sume video rows list supported_input_references per model. The docs show seedance-2 with audio_url, H3 Max with audio, and Gemini Omni Flash 1.1 without it.
Python asyncio.Semaphore sized to a Sume plan's job capacity
Free holds 6 paid jobs at once, Pro 24, Startup 48, Scale 120. A Semaphore of that size keeps a 60-job batch from hitting 429 queue_full.
Node: flip a video backend to Sume a day before the Veo 3.1 shutdown
Google ends three Veo 3.1 preview ids on Oct 22 and its page gives a date, not an hour. A 19-line Node switch moves traffic to Sume early, with an override.
TypeScript SDK: createVideoGeneration, then poll for 'cancelled'
The @sume-com/sdk video functions return {data, error, response} and never throw. An 18-line loop passes an Idempotency-Key and handles the British spelling.
Can Gemini Omni edit change a video's aspect ratio? No
On Sume, Omni's edit mode takes a video_url and a prompt, defaults to 720p and accepts no aspect_ratio or duration. A 16:9 source stays 16:9, so plan the crop.