Free Text Input

Participants write descriptions, transcriptions, or reviews for each item. In unmoderated mode it's a simple textarea. In moderated mode, an AI voice guide reads what the participant wrote and asks adaptive follow-up questions — no two sessions are the same.

Describe what you see

Item Preview
Describe what you see in this image...
Progress2 of 5 completed
Automated

Candor does this so you don't have to

🧍

Independent responses

Each participant writes without seeing others' answers. Item order is randomized per session to eliminate order bias and groupthink.

⏱️

Transcription-aware timing

Estimates 4x media duration for replay and typing tasks. Rewards are calculated so participants are never underpaid for the time they actually spend.

🤖

Adaptive AI moderation

In moderated mode, AI reads written responses and asks follow-up questions in real time. The conversation adapts based on what the participant wrote.

📊

Multi-participant aggregation

Multiple participants respond to the same items. Responses are grouped by item so you can spot patterns instantly across your entire dataset.

01 Under the hood
1

Independent writing

Each participant writes their response independently. Items are presented in randomized order. No one sees what others have written — eliminating groupthink and anchoring effects.

P1
P2
P3
2

AI reads and probes

In moderated mode, the AI voice guide reads the participant's written response and asks adaptive follow-up questions. It probes deeper on interesting comments, explores edge cases, and validates intent in real time.

“The shadows have a blue tint...”
“Can you describe how that affects the mood?”
3

Transcription-aware timing

For audio and video items, Candor estimates 4x the media duration for replay and typing. Reward calculations ensure participants are fairly compensated for the actual time spent on each task.

Media
Allotted
4x
4

Grouped by item

Responses from all participants are automatically grouped by item. You see every response for each asset side-by-side, making it easy to spot patterns and outliers across your dataset.

{ item: "img_01", responses: [3] }
02 What you get back

Responses: Grouped by Item

12 responses collected
IMG_00821_HQ.png4 responses
#P-12

The background elements are slightly out of focus, drawing attention to the primary central object. The lighting feels artificial but warm — almost studio-like.

#P-44

Subject is clear, but the blue tint in the shadows makes it feel clinical. Good contrast overall. Would work well for product photography.

#P-07

Dominant warm tones with a subtle vignette. The composition leads the eye from bottom-left to the center. Slight noise in the darker regions.

clip_narration_v2.mp34 responses
#P-12

The narrator speaks clearly but rushes through the second paragraph. There is a slight echo that suggests a large room. Timestamp 0:14 has an audible breath.

#P-44

Good pacing in the intro. The tone shifts to be more conversational around 0:22. Background hum is consistent but not distracting.

Export all responses as JSON or CSV. Each response includes participant ID, item ID, timestamp, and the full text.
03 Best for

Ready to collect text responses?