Engage in real-time customer support conversations that adapt to user emotions and behavior.
resolve_customer_issue
tool to gather:
product
: what the issue is aboutissue_description
: a short explanation of the problemurgency
: how serious the issue is (low
, medium
, or high
)raven-0
model to watch for signs like fidgeting, slouching, or facial expressions. If the user appears upset, it calls the user_emotional_state
tool with:
emotional_state
: what the user seems to feel (e.g., frustrated, calm)indicator
: what was observed (e.g., sighing, avoiding eye contact)cartesia
voice engine with emotion control.tavus-advanced
engine with smart turn detection for seamless real-time conversations.Step 1: Create a Persona
<api_key>
with your actual API key. You can generate one in the Developer Portal.Step 2: Create a Conversation
<api_key>
with your actual API key.<customer_service_persona_id>
with the ID of the persona you created using the Customer Service Agent configuration.Step 3: Join the Conversation
conversation_url
field to join the conversation: