The respondent experience is the heart of what makes ChatWisp different. Your audience moves through a thoughtfully designed journey from start to finish.
Starting the conversation
Respondents open your link to a welcoming, focused screen. If their browser supports voice, they choose between Voice ("the interviewer speaks, you talk back") and Chat ("read and type at your pace"). If voice is not available, they continue by typing. Any welcome message you added appears here, with a reassurance that they can switch modes or stop any time.
The voice-first stage
For voice, respondents enter a calm, dark stage centered on a living, glowing orb that shows what is happening at a glance — it animates while the interviewer speaks, turns warm coral while listening (a clear "your turn" cue), and dims softly while thinking. On small screens it becomes a compact status pill. A one-tap Captions button reveals the question text for anyone who prefers to read along.
Three ways to answer
Every answer can be given freely:
- Speak — say it naturally; words appear live beneath the microphone.
- Type — open a text box any time.
- Tap — use the on-screen control (stars, NPS bands, a slider, choice cards, drag-to-rank).
The controls are beautiful, brand-colored, and purpose-built for each question type. Respondents can switch between Voice and Chat at any moment without losing their answer.
Answer echoes and adjustments
After each answer, a gentle confirmation shows what was captured — rendered in the question's own visual language (a star count, an NPS band, a formatted email). If the AI heard it wrong, a one-tap Adjust lets them fix it on the spot without disrupting the flow.
A polished finish
When the conversation ends, respondents see a graceful closing screen with your optional outro message, a quick recap, and a warm thank-you.
On mobile
The whole experience is mobile-first: thumb-friendly controls, a large microphone target, safe-area padding around notches, and compact chrome so the conversation stays front and center.