Skip to main content
Personality controls how your agent communicates; voice controls how it sounds. Both are edited on the agent’s detail page.

​
Personality

1

Open the Personality tab

Go to /agents, open an agent, then select Personality (/agents/:id/personality).
2

Choose tones

Pick one or more Tones that describe how the agent should come across (for example, friendly, professional, concise).
3

Describe the personality

Use the Personality text box to add detail about how the agent behaves. Click the generate button (the sparkles icon) to draft a personality from the agent’s language if you’d rather start from a draft.
Your changes are reflected in the agent prompt the next time the agent runs.

​
Voice

1

Open the Voice tab

Select Voice (/agents/:id/voice).
2

Browse and preview

Use the Female and Male tabs to browse available voices. Click the play button next to any voice to hear a short preview.
3

Select and save

Click a voice to select it (a green “Selected” label appears), then click Save.
“Voice updated” confirms the selection was saved to the agent.

​
Troubleshooting

Personality generation needs the agent’s languages set first. Add at least one language on the Overview tab.
Previews are generated on demand. Wait for the spinner to finish, check your device volume, and try a different voice if one fails.
You must have a voice selected before saving. Click a voice in the list first.