Understanding from a photo
One frame is enough
The customer sends a photo of the product, label or part; the agent reads the necessary information and connects directly to the relevant search or action. No technical knowledge required.
- Reading labels, sizes and models
- Automatic search with the read data
- Alternative input for users who can’t type
Visual Recognition Assistantonline
product-label.jpgtool: visual analysisI read the product and content info from the label: 100% orange juice, 500 ml. Shall I bring up allergen and content details or similar products?
Type your message here...
Voice input
Speaking is easier than typing
The mobile user speaks instead of typing; the agent transcribes the voice message to text, understands it and responds with the same intelligence. The flow continues even when hands are busy.
- Transcribing voice messages to text
- Fast, natural experience on mobile
- Accessible, usable by everyone
Visual Recognition Assistantonline
0:06
tool: speech-to-text · intentI understood you want "the nearest service open this weekend". I’m finding it right away.
Type your message here...