Chatbots, Voice Assistants and Conversation Modes

Voice and Chat Are Different

Voice and chat are both conversational interaction modes which makes them very different from programmatic interfaces common in mobile apps and on the web. However, not all conversation is the same. Voice is more limited in what it can do in terms of information sharing and context maintenance and as a result chatbots typically don’t migrate well to voice apps. With a voice-first design you can assure strong performance for voice interactions and adjust the user experience to take advantage of some unique features offered by chatbots.

Chat UX Considerations


When building for both voice and chat the biggest difference is that both chat and voice conversations can be synchronous, but chat can also be asynchronous. With chat, you can have longer pauses between exchanges, context must be maintained across time and surface, and you can introduce multiple agents into the interaction or handoff to other modes. 


Chat is a strictly visual conversation. This often involves only text, but chatbot developers learned long ago that symbols and images can be critical tools both in delivering information to users and receiving it. The visual communication also provides a record of the conversation that a user can refer back to which can enhance the interaction.


Text-based and spoken speech are different. Voice interactions will be dominated by complete sentences that often have less detail than you can deliver via chat and with the key point at the end of the dialog. Chat offers more latitude to deliver longer and more complex information and key points must be at the beginning because users often skim responses.

Multimodal and Single Mode Engagement

Google Assistant today offers a multimodal conversational experience that supports both voice and chat. Every Google Action must be navigable by voice only through a smart speaker but also include a contemporaneous chat experience that enables users to switch to reading or typing on their smartphone or smart display. So, despite their differences, voice and chat are already converging while also requiring separate attention for their unique characteristics. XAPPmedia has already navigated this convergence for several leading brands in insurance, automotive, and consumer packaged goods. Our team can help you define your UX and architecture strategies for a holistic conversational model.