Skip to main content

Voice & Video Modes: How to Switch Interfaces

Accessing the audio and video simulation layers of your agent.

Written by xDitto

Your xDitto clone operates in three modes — text (default), audio, and video. Here's how to switch between them from your dashboard.

1. The mode switcher

In the main chat interface, look just below the text input bar on the left. You'll see two icons.

  • Audio mode: the waveform icon.

  • Video mode: the monitor/play icon.

2. Audio mode

Clicking the waveform icon switches to a voice-only interface.

  • Visual: a dynamic waveform reacts to your voice.

  • Status: "Listening..." means your clone is processing your speech.

  • Use it for: practicing your pitch or answering questions hands-free, like while commuting.

3. Video mode


Clicking the monitor icon brings up your full digital twin.

  • Visual: your generated avatar takes over the screen.

  • Behavior: it maintains eye contact and lip-syncs its responses to you in real time.

  • Use it for: previewing how your clone appears to others in a video conversation.

4. Session controls

Once you're in audio or video mode, two controls sit at the bottom of the screen:

  • Microphone icon: mutes or unmutes your input.

  • Red phone icon: ends the session and returns you to text chat.

Did this answer your question?