Choose your AI interviewer’s voice and configure how participants will interact with your study. These settings shape the participant experience.Documentation Index
Fetch the complete documentation index at: https://docs.userintuition.ai/llms.txt
Use this file to discover all available pages before exploring further.
Overview
In this step, you’ll configure two key aspects of your study:- Interviewer Voice: The voice participants will hear during the conversation
- Interview Mode: How participants will interact with the interviewer (chat, audio, or video)
Choosing Your Interviewer Voice
User Intuition offers two professionally designed AI interviewer voices. Each voice has been optimized for research conversations—warm, professional, and designed to put participants at ease.Elliot
- Gender: Male
- Accent: American
- Tone: Soothing, friendly, professional
Clara
- Gender: Female
- Accent: American
- Tone: Calming, deeper tone, professional
Previewing Voices
To hear what each voice sounds like:- Locate the Elliot or Clara card on the screen
- Click the play button (▶) in the top-right corner of the card
- Listen to a sample of the voice
Tip: We recommend previewing both voices before making your selection. Choose the voice that best represents your brand and will resonate with your target participants.
Selecting a Voice
- Click on the voice card you want to use
- The selected card will be highlighted with a gray background
- Your selection is saved automatically
Configuring the Interview Mode
Below the voice selection, you’ll see the Default Mode settings. These control how participants will interact with the AI interviewer.Available Modes
| Mode | Description | Best For |
|---|---|---|
| Chat | Participants type their responses | Environments where audio isn’t practical; carefully composed responses |
| Audio | Participants speak and hear the interviewer | Natural, conversational research; capturing emotional nuance |
| Video | Video conversation with optional screen share | UX research; capturing facial expressions; product testing |
Mode Details
Chat Mode Participants type their responses in a text-based conversation.- Text-based interface similar to messaging apps
- Participants can take time to think before responding
- Easy to review and edit responses before sending
- Ideal for international studies where language clarity is important
- Voice conversation similar to a phone call
- More natural and conversational flow
- Captures verbal cues and emotional expression
- Ideal for longer interviews where typing would be fatiguing
- Video call experience with optional screen sharing
- Richest interaction mode
- Allows visual demonstration of experiences
- Ideal for user experience research requiring screen observation
Selecting a Mode
- Find the Default Mode section below the voice cards
- Toggle the switch next to your preferred mode
- You can enable multiple modes if needed
Offer incentive
Below the mode settings, you can configure a reward amount for participants who complete interviews. Rewards are sent as digital gift cards via Tremendous and debited from your wallet balance.Setting up incentives
- Enter the dollar amount you want to offer per completed interview (between 250)
- Optionally enable auto-send to automatically distribute rewards after high-quality interviews
You must have a payment method on file to send rewards. If no card is on file, the reward button is disabled and displays “No Card on File” in the Calls tab.
How rewards work
- Rewards are debited from your wallet balance when sent
- You can send rewards manually from the Calls tab, or enable auto-send for automatic distribution
- Only high-quality interviews are eligible for auto-send rewards
- Panel participant incentives are managed separately by User Intuition
Considerations for Mode Selection
By Participant Type
| Participant Type | Recommended Mode |
|---|---|
| Busy executives | Audio (quick, natural) |
| Technical users | Video with screen share |
| International participants | Chat (language clarity) |
| Mobile users | Audio |
| Users with accessibility needs | Chat (works with screen readers) |
By Research Goal
| Research Goal | Recommended Mode |
|---|---|
| Emotional drivers | Audio or Video (captures tone) |
| Usability feedback | Video with screen share |
| Detailed explanations | Chat (participants can compose thoughts) |
| High response rates | Chat (lowest barrier to participation) |
By Interview Length
- Short interviews (5-10 min): Any mode works well
- Medium interviews (10-20 min): Audio recommended
- Long interviews (20+ min): Audio or Video (typing fatigue in chat)
Proceeding to the Next Step
Once you’ve selected your interviewer voice and configured the interview mode:- Review your selections
- Click Save & Continue to proceed to Step 5: Test Your Conversation

