Video sound cue selection: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Describe the current edit beat to compare whoosh, pop, ding, riser, impact and no cue. The result expresses an editing preference rather than analyzing audio or adding a sound effect.
An optional effect should have a purpose in the edit. The choice here uses the described event: a confirmation, a reveal or a motion cue. It does not infer a soundtrack from a keyword alone.
This is a text-only planning exercise. Hearing the original dialogue, checking levels and selecting appropriately licensed audio remain separate production steps. None is a normal outcome, not an API failure.
This independently authored text exercise adapts an edit decision defined in the linked Jev Shorts Editor repository. Its synthetic shots, simplified rules and missing-input outcomes are original to this page. It does not reproduce a rendered edit, inspect video, or verify the repository’s timing and cost claims.

Use the sample to understand the rule, then test your own input for video sound cue selection.

Describe the current edit beat to compare whoosh, pop, ding, riser, impact and no cue.

Open the decision rules and keep the intended distinction between Whoosh, Pop, Ding, Riser, Impact. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review uncertain or unexpected results before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Slide across panels | Whoosh | 100% |
| Small badge appears | Pop | 100% |
| Successful save | Ding | 100% |
| Reveal coming next | Riser | 86.0% |
| Point lands | Impact | 90.0% |
| Quiet explanation | None | 88.0% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
No. It selects a named effect category. Audio production and playback are outside this demo.
The supplied beat does not call for one of the offered effects, or the context is missing. Provider errors appear as errors rather than this content label.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.