Muse Wonder reviews a video: send Sume inspect stills and transcript
Muse Wonder takes video and audio in but replies only in text. To have it review a Sume render, use video_inspect: 8 stills by default, 24 at most.

To have Meta's Muse Wonder review a clip you rendered on Sume, call video_inspect and pass the model its stills and transcript as text and images. By default Sume returns 8 stills at up to 768 px, and a single call can return at most 24 stills from a source up to 1,800 seconds long.
Meta's model page lists text, image, video, audio and PDF as input, text as the only output, and a 1,048,576-token context window (read 2026-10-13).
Why not hand the model the MP4 directly?
Native video input may work, but the sources I read give no limits for it: no maximum duration, file size or frame rate. Sume's route has documented limits and returns small, checkable pieces. The video inspect page says the route reads one media.sume.com clip the workspace already owns, never re-encodes it and never makes an MP4.
A clip from another host has to be imported first with POST /v1/media-imports; the API rejects off-host URLs at admission. Inspect then returns a probe object, frames[{t,url,width,height}] as durable image artifacts, and optionally a transcript.
What does one inspect call give the model?
The frames field controls the stills. Only one of at[] or fps may be sent, never both. Raise max_edge (64 to 2160) if the reviewer must read on-screen text. Use seek: "precise", the default, when the timestamp matters; fast can return a still up to one GOP early, roughly 0 to 5 seconds on typical sources.
| frames value | What comes back | Limit |
|---|---|---|
| not sent | 8 mid-bin stills (1 fps if the clip is under 8 s) | 768 px longest edge |
| false | Probe only, no stills | none |
| { at: [seconds] } | Stills at the instants you name | 1 to 24 values, each 0 or more |
| { fps: n } | Evenly sampled stills | 0 < n <= 2, capped at 24 stills |
How do I give it the audio?
Send transcribe: true and the response includes transcript with text, words[] and optional sentence segments[]. This is the billed part: Sume reserves one minute unless you send duration_seconds (maximum hint 600), and the credits scale with audio minutes at the API rate card.
Check probe.has_audio first with a frames: false call. A silent clip with transcribe: true returns inspect_source_has_no_audio.
How does the agent wire it together?
Inspect is the hosted MCP tool video_inspect. A write needs idempotency_key (and mcp:write under OAuth). The default mode is sync and waits at most 30 seconds; on a 202 the agent polls with jobs_wait and then jobs_result, as listed on MCP tools and gates.
Muse Wonder is listed on OpenRouter as a chat-completions model, so the review call is a normal chat request that carries the still URLs and transcript text. Whatever it replies is text; to fix what it finds, the agent calls Sume's generation tools again. Keep the stills small: eight 768 px frames and a transcript are enough to catch a wrong product, a garbled caption or a mismatched voice, and each still is a durable media.sume.com URL the model can cite back by timestamp t.
- Review a 30-second ad:
fps: 0.5gives 15 stills, as in this walkthrough. - Check a long render: 24 stills plus a transcript, as in this one.
- Start from a URL: import first, then inspect, as in this one.
Sources
Related posts
More in Models
- Nano Banana 2.1 thinking levels and search grounding: not on Sume
fal documents thinking levels, web-search grounding and a system prompt for Nano Banana 2.1. Sume's /v1/images row lists none and returns 400 for them.
- Nova 2.5 Sonic turn-taking: does a voiceover need it?
No. Controllable turn-taking and mixed voice and text sessions in Nova 2.5 Sonic serve live agents. A rendered voiceover is one script in, one file out.
- Qwen Image 2.1 Pro API price: $0.04 in Singapore, $0.0353 elsewhere
Alibaba lists qwen-image-2.1-pro at $0.04 an image in Singapore and $0.035333 elsewhere. Sume has no 2.1 Pro row; its Qwen rows bill $0.025 and $0.094.
- Qwen Image 2.1 Turbo API price: $0.016 per image, and Sume's Qwen row
Alibaba lists qwen-image-2.1-turbo at $0.016 per image in Singapore. Sume does not list 2.1 yet; its Qwen Image row bills $0.025.
Written by Sume