write_reference_result
Writes analyzed video reference data to the editor after frame analysis, automatically populating detected slots and handling persistent text overlays across multiple scenes.
Instructions
Write your analysis of the reference video frames back to the editor. The editor modal will automatically populate with the detected slots.
Call this after get_reference_frames. For text that appears across MULTIPLE consecutive slots (e.g. hook text while background clips change, or "Students who follow me and use:" over all technique slots), put it in spanning_texts — NOT in each slot's detectedText. Each slot's detectedText should only contain the unique text for that slot (e.g. "GAMIFICATION", "PAST PAPERS").
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| slots | Yes | Analyzed slots, one per scene. Leave detectedText empty for slots covered by a spanning_text. | |
| spanning_texts | No | Text overlays that persist across multiple consecutive slots (e.g. hook text shown while background clips change). | |
| hookTextY | No | Y position for hook text overlay. Range: 1=top, 0=center, -1=bottom. Measure from reference frames: y = 1 - 2*(pixels_from_top / frame_height). | |
| spanningTextY | No | Y position for the spanning/persistent text (e.g. "Students who follow me and use:"). Must be ABOVE slotTextY (higher value). Measure from reference frames. | |
| slotTextY | No | Y position for per-slot technique text (e.g. "GAMIFICATION"). Must be BELOW spanningTextY (lower value). Measure from reference frames. |