Scenario Veo Video
Overview
Veo, Google's video family on Scenario, ships four members at authoring time: Veo 3.1 (full quality,
reference images with a style switch), Veo 3.1 Fast (same modes, quicker, no switch), Veo 3.1 Lite
(frame anchors only, cheapest), and Veo 3.1 Extend Video (continues a clip). Discover them with
search and treat model_schema_get as the contract: members agree on parameter names and disagree
on which inputs exist at all.
Connection and the core loop: see the scenario skill in this repo; model-agnostic video work: the
scenario-video skill. If a sibling skill named here is missing from your available skills, load it
with skill_get (Scenario MCP) or ask the user to install it
(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag
the gap.
Quick reference
Mode follows from the inputs (names from the live schema):
| Mode |
Inputs |
Behavior |
| Text |
prompt |
aspectRatio 16:9 or 9:16 |
| First frame |
image (+ prompt) |
opens on that frame; a mismatched image may be cropped |
| Transition |
image + lastFrameImage |
bridges the stills; prompt one continuous move |
| Reference |
referenceImages (1 to 3) |
subject or style consistency; duration locked to 8 |
| Extend |
video (Extend member) |
continues the clip; 16:9 source, short side 720p or 1080p |
image and referenceImages are mutually exclusive. referenceImagesType exists on full Veo 3.1
alone and reads the whole array one way: ASSET (default) carries subjects, objects, and scenes;
STYLE carries palette, lighting, and texture. Fast takes references without the switch; Lite takes
none. Shared across the three generators at authoring time: negativePrompt, resolution (720p,
1080p), duration (4, 6, or 8 seconds), and seed. generateAudio is required on every member
and moves the price. The Extend member takes only prompt, video, generateAudio, and seed: no
duration, resolution, or ratio controls. At authoring time price spanned roughly five times between
Lite and full 3.1 for one image-to-video job, and one extension cost more than a fresh full
generation, so aim for the shot in one 8 second pass and dry_run the same payload on two members
before a batch.
The soundstage is in the prompt
With generateAudio: true, Veo renders synchronized dialogue, effects, and ambience, and it takes
audio direction literally. Put spoken lines in quotation marks, prefix effects with SFX: and room
tone with Ambient noise:. A prompt with no audio direction still gets a soundtrack, just not the
one you meant. When a clip needs silence for later scoring, set generateAudio: false rather than
prompting for quiet.
Prompt one continuous shot
Write present-tense prose ordered as cinematography, subject, action, context, style: camera and
shot scale first, one primary arc, roughly 90 to 250 words. For several beats in one clip, timestamp
lines work ([00:00-00:02] Medium shot...), spans fitting inside the chosen duration.
Worked example: a dialogue shot from character references
search with target="models", query="veo", public=true. Prefer the newest non-deprecated
hits, e.g. model_veo3-1 and model_veo3-1-fast (live hits at authoring time: re-discover each
session).
model_schema_get on the chosen id: confirm which reference inputs exist before writing the
payload.
upload_asset two character stills (see the scenario skill) to get asset ids.
model_run with that model_id, dry_run=true, and
parameters={"prompt": "Medium shot, the knight lowers her visor and says, \"Hold the line.\" Torchlight flickers on wet stone. Ambient noise: distant thunder. SFX: metal visor clank.", "referenceImages": ["asset_a", "asset_b"], "referenceImagesType": "ASSET", "duration": 8, "resolution": "1080p", "aspectRatio": "16:9", "generateAudio": true}.
Estimate the same job on the Fast id (drop referenceImagesType, absent there) and compare.
- Repeat
model_run with wait=false, then jobs_wait with the returned job id, re-called with
pending_job_ids on timeout, never a second model_run.
asset_display the output and review with sound. To iterate on wording alone, hold an explicit
seed fixed across reruns.
Common mistakes
- Combining
image with referenceImages: mutually exclusive; pick the opening state or
consistency.
- Any duration but 8 with
referenceImages: reference mode supports only 8 seconds.
- Sending
referenceImages to Lite or referenceImagesType to Fast: the schema decides which
inputs exist.
- Omitting
generateAudio: it is required on every member; pass it explicitly.
- Extending a 9:16 clip: Extend takes 16:9 sources with a 720p or 1080p short side only.
- Writing the prompt as a list of negatives: describe the wanted scene, reserve
negativePrompt for
what to discourage.
1---2name: scenario-veo3description: "Use when generating or extending video with Google Veo models on Scenario via MCP: text-to-video, image-to-video from a first frame, first and last frame transitions, reference-to-video (R2V) with asset or style reference images, native audio with dialogue, sound effects, and ambience, negative prompts, seeded reruns, extending a 16:9 clip, or choosing a quality, fast, or lite tier. Keywords: Veo 3.1, Veo 3.1 Fast, Veo 3.1 Lite, Extend Video, Google, T2V, I2V, V2V, 720p, 1080p."4license: MIT5metadata:6 source: https://skillmd.com/skills/scenario-labs/scenario-veo7---89# Scenario Veo Video1011## Overview1213Veo, Google's video family on Scenario, ships four members at authoring time: Veo 3.1 (full quality,14reference images with a style switch), Veo 3.1 Fast (same modes, quicker, no switch), Veo 3.1 Lite15(frame anchors only, cheapest), and Veo 3.1 Extend Video (continues a clip). Discover them with16`search` and treat `model_schema_get` as the contract: members agree on parameter names and disagree17on which inputs exist at all.1819Connection and the core loop: see the `scenario` skill in this repo; model-agnostic video work: the20`scenario-video` skill. If a sibling skill named here is missing from your available skills, load it21with `skill_get` (Scenario MCP) or ask the user to install it22(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag23the gap.2425## Quick reference2627Mode follows from the inputs (names from the live schema):2829| Mode | Inputs | Behavior |30| ----------- | -------------------------- | --------------------------------------------------------- |31| Text | `prompt` | `aspectRatio` 16:9 or 9:16 |32| First frame | `image` (+ `prompt`) | opens on that frame; a mismatched image may be cropped |33| Transition | `image` + `lastFrameImage` | bridges the stills; prompt one continuous move |34| Reference | `referenceImages` (1 to 3) | subject or style consistency; `duration` locked to 8 |35| Extend | `video` (Extend member) | continues the clip; 16:9 source, short side 720p or 1080p |3637`image` and `referenceImages` are mutually exclusive. `referenceImagesType` exists on full Veo 3.138alone and reads the whole array one way: `ASSET` (default) carries subjects, objects, and scenes;39`STYLE` carries palette, lighting, and texture. Fast takes references without the switch; Lite takes40none. Shared across the three generators at authoring time: `negativePrompt`, `resolution` (`720p`,41`1080p`), `duration` (4, 6, or 8 seconds), and `seed`. `generateAudio` is required on every member42and moves the price. The Extend member takes only `prompt`, `video`, `generateAudio`, and `seed`: no43duration, resolution, or ratio controls. At authoring time price spanned roughly five times between44Lite and full 3.1 for one image-to-video job, and one extension cost more than a fresh full45generation, so aim for the shot in one 8 second pass and `dry_run` the same payload on two members46before a batch.4748## The soundstage is in the prompt4950With `generateAudio: true`, Veo renders synchronized dialogue, effects, and ambience, and it takes51audio direction literally. Put spoken lines in quotation marks, prefix effects with `SFX:` and room52tone with `Ambient noise:`. A prompt with no audio direction still gets a soundtrack, just not the53one you meant. When a clip needs silence for later scoring, set `generateAudio: false` rather than54prompting for quiet.5556## Prompt one continuous shot5758Write present-tense prose ordered as cinematography, subject, action, context, style: camera and59shot scale first, one primary arc, roughly 90 to 250 words. For several beats in one clip, timestamp60lines work (`[00:00-00:02] Medium shot...`), spans fitting inside the chosen duration.6162## Worked example: a dialogue shot from character references63641. `search` with `target="models"`, `query="veo"`, `public=true`. Prefer the newest non-deprecated65 hits, e.g. `model_veo3-1` and `model_veo3-1-fast` (live hits at authoring time: re-discover each66 session).672. `model_schema_get` on the chosen id: confirm which reference inputs exist before writing the68 payload.693. `upload_asset` two character stills (see the `scenario` skill) to get asset ids.704. `model_run` with that `model_id`, `dry_run=true`, and71 `parameters={"prompt": "Medium shot, the knight lowers her visor and says, \"Hold the line.\" Torchlight flickers on wet stone. Ambient noise: distant thunder. SFX: metal visor clank.", "referenceImages": ["asset_a", "asset_b"], "referenceImagesType": "ASSET", "duration": 8, "resolution": "1080p", "aspectRatio": "16:9", "generateAudio": true}`.72 Estimate the same job on the Fast id (drop `referenceImagesType`, absent there) and compare.735. Repeat `model_run` with `wait=false`, then `jobs_wait` with the returned job id, re-called with74 `pending_job_ids` on timeout, never a second `model_run`.756. `asset_display` the output and review with sound. To iterate on wording alone, hold an explicit76 `seed` fixed across reruns.7778## Common mistakes7980- Combining `image` with `referenceImages`: mutually exclusive; pick the opening state or81 consistency.82- Any duration but 8 with `referenceImages`: reference mode supports only 8 seconds.83- Sending `referenceImages` to Lite or `referenceImagesType` to Fast: the schema decides which84 inputs exist.85- Omitting `generateAudio`: it is required on every member; pass it explicitly.86- Extending a 9:16 clip: Extend takes 16:9 sources with a 720p or 1080p short side only.87- Writing the prompt as a list of negatives: describe the wanted scene, reserve `negativePrompt` for88 what to discourage.