Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
sume/auto or a pinned image model: what the response shows
With sume/auto, job.model stays sume/auto, the model list omits it and the family is never named. A pinned id echoes back as requested.
A Sume image job at 50 seconds: slow, queued, or stuck?
Sume's docs say an image still running after a 50 s jobs_wait is usually stuck, not slow. Check queued vs processing and events first; never submit twice.
STT language: Sume language_code hint vs the 60 languages MAI lists
Sume STT takes an optional language_code and auto-detects when omitted. A tracker lists MAI-Transcribe-2-Streaming at 60 languages; Sume's docs state no count.
Talking presenter: Fabric still plus voice, or video model plus voice?
Sume docs: video models do not lip-sync to TTS, so use a still plus audio on Fabric ($0.1875/s at 720p listed). Wan 3.0 is cheaper but will not match the voice.
Timeline audio concat or audio.parts: which join for narration takes?
Use audio.parts when the narration only feeds one render; use Timeline audio concat when you need a reusable file. Concat is $0.01 per job, up to 1,800 s.
Timeline output fps: omit it to follow your clips, or get a warning
Leave output.fps out and Timeline 1.0 follows your longest video sources. Force 30 on 24 fps clips and the job warns output_fps_resamples_sources.
Transcribe a 90-second clip with video inspect: cost and reservation
Video inspect with transcribe true adds Sume STT at $0.01 per audio minute; send duration_seconds 90 so the hold fits, or it reserves one minute.
Sume video poll usage.cost: reserved while running, captured at end
The usage.cost number is the Sume billable amount: the reservation while a job runs and the captured amount once it settles. wan-3.0 at 720p, 10 s, as math.
Video frames caps at 24 stills: a 15 s hook needs fps 1.6, not 2
Video frames returns at most 24 stills and fps up to 2. At 2 fps only 12 s are covered, so a 15 s hook needs fps 1.6; the Python below checks any length.
Old prompt says video-router_create? Sume now takes generate_video
Sume retired the hosted MCP tool name video-router_create for generate_video and maps dots to underscores. Update the prompt, then check tools_list.
Vidu Q4 takes 15 image refs: what Sume's reference limits are
Vidu Q4 Preview lists up to 15 image and 3 audio references. Sume does not list Vidu; Gemini Omni Flash 1.1 takes 10 images and 3 clips of 3 s, none audio.
VS Code mcp.json: put the Sume API key in a password input
In VS Code, declare a promptString input with password true and reference it as ${input:id} in the x-api-key header, so the Sume key never lands in mcp.json.
VS Code mcp.json for Sume: set type http, not sse
VS Code accepts type http or sse for a remote MCP server. Sume documents a streamable HTTP endpoint at https://mcp.sume.com/mcp, so use type http and a url.
Wait for an avatar video in one request? Sume sync stops at 30 s
Sume sync and subscribe modes are the same bounded wait of at most 30 seconds. For avatar videos use async with polling or a webhook, not a long HTTP hold.
A 1.5-second clip allows a 0.75-second fade: Timeline limits
Timeline 1.0 caps a transition at 1 second and 50% of the shorter neighbor clip. Table of the maximum fade for 0.5 to 4 second clips, plus the refusal codes.
A/B test two video models: pin the ids, sume/auto hides the family
sume/auto always reports model sume/auto and never discloses the family that ran, so it cannot A/B two models. Pin both ids; a 5 s 480p pair costs $0.76.
Edit returns a square? A 1-cent test for aspect_ratio auto vs none
Omitting aspect_ratio on a Sume edit is not the same as auto. A 1-cent low-quality regression test that catches the dropped field before it ships.
AI presenter for YouTube Shorts: format limits and Sume output
Shorts can be square or vertical and run up to three minutes. Sume avatar videos are 9:16 or 1:1 at up to 60 seconds per job, so one job fits a Short.
AI spokesperson video for TikTok ads: a spec check against Sume
TikTok recommends 9:16 with at least 540x960 for non-Spark ads. Sume avatar videos default to 9:16 at 720p. What to verify before you upload.
API Gateway to Lambda: verify a Sume video webhook on the raw bytes
A Sume callback_url can point at a Lambda behind an HTTP API. Decode the body to bytes first, then verify sume-v1 with the SDK. Handler code is under 30 lines.
Six stills and a logo clip as references: Wan 3.0, Omni, H3 or Kling?
For a brand-kit video with six stills and one logo clip, Wan 3.0 and MiniMax H3 fit; Omni caps clips at 3 s; Kling 3 takes no references. 8 s prices inside.
Bulk queue key from a payload hash: same body 202, new body 409
Derive a Format bulk queue Idempotency-Key from a sha256 of its body. The same body replays 202 with the old queue; a changed body gives 409.
dry_run or generation_admission_preview first for 12 Sume clips?
Use dry_run on a paid call for its estimate, and generation_admission_preview before a burst of 12 clips to check balance and queue room. Neither submits a job.
Edit a clip, swap a person, or move motion onto photos: 3 Sume models
Omni Flash edits a clip by prompt ($1.25 per 10 s, 720p), H3 Max Recast swaps people ($3.75, 768p), Genjutsu moves motion onto photos ($3.98, 480p).
Get a 30-second track from Music 1.0 when there is no duration field
Music 1.0 rejects duration and duration_seconds. Steer length in the prompt, for example 'a 30-second track' with timestamped sections; a generation is $0.125.
GPT Image 2.5 slow? OpenAI says jpeg is faster than png
OpenAI says jpeg is faster than png and complex prompts can take 2 minutes. How to set output_format on Sume and handle the 202 that follows.
Korean captions on a small phone: clip-wipe or black-outline?
Sume lists six Hangul caption styles. The docs call black-outline the safe default and clip-wipe the clearest at small phone sizes. Fonts and the 400 rule.
MAI-Voice-2.1 or Sume TTS for a presenter ad read: 3 prices
For a 700-character ad read, MAI-Voice-2.1 is about 1.5 cents, Flash 1 cent and Sume TTS 4 cents. Fabric needs the audio as a public URL.
mask_url edit on GPT Image 2.5: the mask is a guide, not a hard edge
OpenAI says GPT Image masking is prompt-based and may not follow the mask shape exactly. How that affects mask_url edits on Sume and a cheap way to test it.
Music Router negative_prompt: send an empty string, not a list
Sume Music Router takes negative_prompt only omitted or as an empty string. Put exclusions in the prompt. Duration is refused too. Price stays $0.125.
Narration cost per minute at 900 characters a minute: Flash vs Sume
At an assumed 900 characters per minute, Sume TTS runs about 4.3 cents a narrated minute; MAI-Voice-2.1 lists near 2 cents and Flash near 1.4 cents.
Unattended agent on Sume MCP: API key or OAuth consent?
A cron or CI agent cannot click a consent page. Sume's docs give OAuth to interactive clients and API-key remote MCP to automation, with caps set per call.
PowerShell 7: verify a Sume webhook with HMACSHA256, constant-time
A PowerShell function that refuses an empty secret, checks the 300-second window and accepts any entry in a rotated sume-v1 header. Under 30 lines.
Seedance 2.5 costs 1.53x Seedance 2.0 at 720p for 10 seconds
A 10 s 9:16 clip at 720p is $5.78 on Seedance 2.5 and $3.78 on Seedance 2.0 on Sume. What the extra $2.00 buys, and the ratio at 480p and 1080p.
sonic-latest or sonic-3-6: which Sume TTS id for repeatable narration
Pin sonic-3.6 when a series must sound the same; sonic-latest is an alias that tracks the current stable Sonic. Avoid sonic-preview with pro voice clones.
Sume MCP with Write off: what an OAuth agent can still do
With OAuth read-only (mcp:read), an agent on Sume's hosted MCP can still read jobs, assets and the catalog and scrape pages. Writes and paid tools fail.
Sume /content?index=N: default 0, a 302, and a 404 past the last one
What the Sume content route answers for index 0, an index past the last output, a failed job and a running job, plus a Python loop that saves every output.
Self-test a Python Sume verifier: rotation, stale time, empty secret
Six asserts for a stdlib hmac verifier: new and old secret both pass, tampered body fails, 301 seconds old fails, empty secret raises. One file, no framework.
TikTok ad: 500 MB over 10 minutes caps bitrate near 6.7 Mbps
TikTok non-Spark ads allow 10 minutes and 500 MB, with a 516 kbps minimum. Sume Timeline sets no bitrate, so check your exported file against the arithmetic.
Timeline sizes for TikTok's three ad ratios: 540x960, 960x540, 640x640
TikTok's non-Spark minimums are 540x960 (9:16), 960x540 (16:9) and 640x640 (1:1). All three fit Timeline's even 256 to 2160 px output range at $0.10 a minute.
Verify a Sume avatar video webhook signature in Python
A Python verifier for Sume job webhooks: HMAC SHA-256 over timestamp.raw_body, sume-v1 entries, a 5-minute window, and a refusal when the secret is empty.
Verify the Sume signature in the HTTP handler, not in the queue worker
A queue delay over 300 seconds makes a valid Sume signature look stale. Verify at receipt, enqueue the verified event, and use redeliver if a late check failed.
Which Sume Format for a UGC ad? Read io, then call by name
Sume's catalog lists UGC-style Formats such as sume-close-camera-ugc and sume-mobile-app-ugc. Read each Format's io profile, then run it with a spend cap.
Which Sume video models list auto or adaptive aspect for a start image
Seedance 2.x and Wan 3.0 list auto and adaptive aspect; Kling 3 and Omni Flash list fixed ratios only. What to send when your still is not 16:9.
45-minute recording: audio detach fails past 1800 s, what to do
Sume audio detach accepts a source up to 1800 seconds and returns up to 900. A 45-minute video is 2700 s, so trim first. Here is the arithmetic.
A 61-second audio spine reserves 2 timeline minutes, 60 s reserves 1
Timeline 1.0 reserves $0.10 per ceil(audio minute). A 60 second spine reserves $0.10, 61 seconds reserves $0.20, and 1,800 seconds is the $3.00 ceiling.
Sume ignores aspect_ratio when image_size is set: Flux, Seedream
On Sume's custom-pixel image rows, image_size wins and aspect_ratio is ignored. Nano Banana turns WxH into an enum ratio. What each model does with both fields.
Ad audio spec table: YouTube 48 kHz, Meta AAC 128 kbps, LinkedIn AAC
What YouTube, Meta Facebook Feed and LinkedIn say about video ad audio, and the Sume settings that keep, drop or extract it: trim audio, detach, timeline gain.