Audio Response for AI Agents

We are excited to introduce a new feature that allows agents integrated with ZApi, WhatsApp Official, or Telegram to respond to audio messages with AI-generated voice replies. This means:

  • When a user sends a text message, the agent will reply in text.
  • When a user sends a voice message, the agent will reply with an AI-generated audio response.

Prerequisites

To enable this feature, your organization must provide API keys for:

  1. Groq API Key - Enables high-quality, free audio transcription.
  2. ElevenLabs API Key - Generates AI-powered voice responses.

These API keys must be added to your organization settings.

Configuring Audio Responses for an Agent

Once API keys are added, you can configure audio responses for an agent by:

  1. Navigating to the Deploy tab in the agent settings.
  2. Selecting one of the integrations (ZApi, WhatsApp Official, or Telegram).
  3. Accessing the Settings for the chosen integration.
  4. Choosing the agent’s voice profile or disabling audio responses if needed.

Benefits of Audio Responses

  • Enhances user experience with natural-sounding AI replies.
  • Improves engagement by matching the communication style of users.
  • Supports multilingual conversations with AI-driven speech synthesis.

Try It Now!

Start using AI-generated audio responses today by adding your API keys and configuring your agent’s voice settings!

For more details, visit our Help Center or contact support.