Output Modes
Choose whether your companion responds with audio, text, or both.
The Output Format setting in the Communication section controls how your companion delivers its replies.
Available Modes
You can select one or both output modes. At least one must be active at all times.
Audio
When audio is enabled, your companion speaks its replies out loud with a live text transcript appearing alongside the audio. This creates a conversational, voice-first experience.
Best for: Companions that feel like talking to a real person -- customer support, personal advisors, interactive product guides.
Text Only
When text-only is enabled, your companion responds with written messages only -- no voice output at all. This is a traditional chatbot experience.
Best for: Situations where audio would be disruptive (office environments), when users prefer reading, or for companions that deal with detailed written content.
Using Both
You can have both Audio and Text enabled at the same time. This is the default when you create a new companion. With both enabled:
- Users who want a voice experience get spoken replies with transcripts
- The companion can adapt to how users prefer to interact
Changing the Output Mode
- Go to the Behaviour tab
- Find the Output Format section in the Communication card
- Click the mode you want to toggle on or off
- The selected mode will show a checkmark and a highlighted border
- Remember that at least one mode must stay active -- you cannot deselect both
If you have audio enabled, make sure to check your Voice settings -- the voice, speed, and listening settings will all affect the audio experience.
Last updated on