Druid Voice

Druid Voice provides an end-to-end voice layer for conversational AI, bridging telephony and web-based voice channels with the Druid AI Platform. At its core, Druid SIP acts as the central hub connecting voice engagement channels—including public telephony providers, contact centers, enterprise communication platforms, and WebRTC applications—to the Druid agent framework.

This architecture enables real-time, natural conversations by processing interactions through Speech-to-Text (STT) and Text-to-Speech (TTS) services. Druid Voice supports both native speech capabilities and third-party integrations, offering the flexibility to customize voice experiences to specific enterprise requirements.

NOTE: Druid Voice is available as a tenant feature in technology preview starting with Druid 9.20. To activate it, contact your Druid representative to receive the required connection details.

Prerequisites

The Druid Voice feature must be active on your tenant.
You must have a published AI Agent.