Pantry Checker (plugin type pantry_checker) is a purpose-built image-capture format: respondents take a flexible number of photos, with an early-exit button once a minimum is reached, then optionally answer a voice follow-up. It's wizard-driven.
What respondents see#
A greeting screen introduces the exercise. The respondent captures photos one at a time — each with its own instruction text, framing overlay, and orientation requirement. A "No More Photos" button appears once they've reached the configured minimum, letting them stop early instead of being forced to hit a fixed count. After photos, an optional voice narrative can be recorded.
When to use it#
- In-home usage or pantry/product-presence audits where the number of relevant items varies by respondent, so a fixed photo count doesn't fit.
- "Show us everything you have of X" studies where some respondents have 1 item and others have 4.
- Anywhere Guided Story With Image Capture's fixed count is too rigid.
Configuring it in the builder#
Drag Pantry Checker from the StorySync AI Qual group onto your canvas — the wizard opens with Questions, Display Settings, and Text for Alerts. The Questions step's Image Section is the distinctive part:
- Greetings Text and Instructions — the welcome screen(s).
- Maximum Number of Images — the photo ceiling (1–4).
- Minimum Number of Images — the "No More Photos" button only appears once the respondent has reached this count; must be ≤ the maximum.
- Ask voice follow-up after image capture — toggle the narrative step on or off.
- Per image slot: Instruction Text, Overlay Template, Select Orientation, Custom Rules, and Image Tags.
- Instruction Text has a rich text editor (bold, lists, alignment and so on), and the formatting shows on the respondent's camera screen. Custom Rules are plain text boxes, one rule per box: the AI reads them to check each photo, so formatting has no effect there.
Settings reference#
| Setting | What it controls | Default |
|---|---|---|
| Maximum Number of Images | Photo ceiling the respondent can capture | 2 |
| Minimum Number of Images | Photos required before the early-exit button appears | 1 |
| Ask voice follow-up after image capture | Whether a spoken narrative follows the photos | On |
| Voice Mandatory | Voice input required for the follow-up narrative | Off |
| Show Transcription | Live transcript while the respondent talks | On |
| Default to Voice | Voice recording is the default input method for the follow-up (only shown when Voice Mandatory is off) | On |
| Request Voice or Text Preference | Ask respondents whether they'd rather record or type (only when voice isn't mandatory) | Off |
| Tap to Zoom Image | Let respondents tap the concept image to zoom in | Off |
| Enable Image Scrolling | Let respondents scroll through multiple images | Off |
| Enable Auto Probing | Automatically probe on any question if the response is too short or lacks detail | Off |
| Use Whole Conversation | Feed the entire prior conversation into AI-generated probes | Off |
| Auto Capture | Automatically take the photo once framing guidance is satisfied, instead of a manual shutter tap | Off |
| Real Time Image Guidance | Live on-screen feedback while framing the shot (only shown when Auto Capture is on) | On |
| Allow Image Upload | Let respondents upload an existing photo instead of using the camera live | Off |
| AI Source | Which AI engine analyzes captured images (for Image Tags / Custom Rules) | Gemini (or ChatGPT) |
| Is Loaded from Iframe | Marks the question as embedded in an iframe inside an external survey | Off |
| Enable Voice Attribute Detection | Detect speaker gender/age/language/accent/human-vs-AI | On |
| Honor voice-permission globals | Follow survey-level voice/mic-permission setting, auto-skip if unavailable | On (recommended) |
| Concept Image Height | Height of the stimulus image as % of screen | 50% (range 30–70) |
| Question Font Size | Font size for question/instruction text | 17px (range 10–40) |
| Maximum Recording Duration | Cap on the follow-up narrative | 5 minutes (range 3–10) |
| Select Language | Speech-recognition language | English (+ 6 others) |
| Select Text Direction | LTR or RTL layout | Left to Right |
| Button Color | Primary action-button color | #34ac8b |
| "No More Photos" Button Text | Label on the early-exit button in Text for Alerts | "I have no more photos to take" |
Logic support#
Stores a variable-count set of images plus an optional open-ended narrative — condition operators are limited to Answered/Not answered. See Logic, Flow & Conditions.
Good to know#
- Minimum Number of Images must be less than or equal to the maximum — the "No More Photos" button simply won't render if minimum equals maximum, since there's nothing left for it to skip.
Related guides#
- Question Types — overview and when-to-use table
- Guided Story With Image Capture — the fixed-count image-capture sibling
- StorySync AI Qual — all 9 StorySync formats
- Logic, Flow & Conditions — operators and condition builder
Was this page helpful?