Type
Purpose
Data Points
Receiver & Credentials
Review
Save
Deploy

Step 1: Select Voice Agent Type

Choose the workflow type. Recording: greet → instruct → record → thank. Live: real-time dialogue. No TTS: show instructions only, record up to 3 min, then save.

Step 2: Purpose

Speak: English/Hindi use browser voice; Telugu/Tamil/Kannada/Malayalam use Google TTS via server.

Collect User Info (optional)

Fields to collect from the user before they see instructions. Key = internal name; Label = text shown on the public agent page.

Step 3: Data Points Collection

Define what data you want to extract from conversations. Each field will be collected during or after the conversation.

Step 4: Receiver, Credentials & Voice of AI

Describe who receives the call, who arranged it, and how the AI should sound.

Describe the role, designation, or type of person who will receive calls from this agent.
Describe the person, team, or department who arranged this call setup.
Define the personality, tone, and speaking style of the AI agent.

Step 5: Review & Edit

Review your configuration. You can navigate to any step to make changes.

Configuration Summary

Step 6: Save Agent

Name your agent and save. All required fields must be filled.

Database connection (optional)

Template for data points storage. Saved to a text file named after the table name.

Step 7: Deploy Voice Agent

Your agent is ready! Share this link to start using it. The link can be shared with anyone who needs to interact with the agent.

Back to Agents