Announcement

The Vodia PBX and Google Gemini

Published on:

February 4, 2026

Vodia PBX now integrates Google Gemini with JavaScript IVR and Voice Agents, enabling real-time, AI-driven call handling and intelligent routing. By combining Gemini’s multimodal large language models with Vodia’s programmable IVR framework, organizations can build voice agents that stream audio in real time, make routing decisions through function calls, and handle both basic and attended transfers with AI-assisted screening. This integration allows businesses to automate call flows, reduce hold times, and improve productivity using conversational AI that works directly inside the PBX.

Vodia Networks is pleased to announce the integration of Google Gemini (“Gemini”) with Vodia Javascript IVR capabilities. Gemini enables users to directly collaborate with generative AI, with direct access to current Google AI models. It’s an interface to a multimodal Large Language Model (LLM), one that handles audio, images, and text. 

Gemini Personal Intelligence

On January 20, 2026, Gemini introduced Personal Intelligence - the platform can now be connected to a user’s Google apps for personalized Gemini experiences (users can choose which apps are connected via their Connected Apps settings):

  • Personalize experiences with insights about individual users and their preferences/relationships
  • Make recommendations derived from user preferences
  • Create bespoke itineraries
  • Discover and summarize information from a user’s Google apps, i.e., what did I search for on Google last week, etc.
  • Access Gmail and Google Photos content

Vodia JavaScript IVR

Vodia's JavaScript brings the full power of a modern programming language to telephone interactions, creating immeasurable flexibility for customized call flows and integration with external systems. Our simple IVR script contains the IVR system’s core capabilities: Text-to-Speech (TTS) output, DTMF (touch-tone) input collection, and communication with external applications. This framework provides dynamic responses based on real-time API calls, enabling intelligent call routing.

Voice Agents JS - Gemini Basic Call Transfer 

The integration of the Vodia phone system with Gemini brings impeccable call transfer functionality to any cloud communication ecosystem. 

Basic Voice Agents script can leverage the power of Gemini, thanks to an integration with Vodia's JavaScript Voice Agents capabilities. This integration uses the Gemini bidirectional audio streaming WebSocket API to manage both real-time voice conversations and intelligent call routing:

  • Configure the session with model parameters, voice settings, and system instructions
  • Define function tools Gemini can call for call routing (transfer_call)
  • Establish a WebSocket connection to Gemini's bidirectional streaming API endpoint
  • Manage error conditions and timeout scenarios with fallback transfers
  • Parse Gemini's function call responses to determine appropriate call routing
  • Play audio responses from Gemini back to callers
  • Stream PCM audio from the caller to Gemini in real-time

Documentation for this integration is provided in the Voice Agents JS Example – Gemini Basic Call Transfer documentation.

Voice Agents JS - Gemini Attended Call Transfer

Once integrated with the Vodia PBX, Gemini functions as an intelligent screening assistant for attended transfers. Rather than manually calling other users to confirm availability, users have access to the system’s AI Voice Agents to screen and connect calls automatically.

One-Button Screening

The integration of the Vodia PBX with Gemini enables attended transfer with AI screening with a single button on a user’s desk phone. How does it work?

AI-assisted attended call transfer using a desk phone and Voice Agents diagram
  1. Caller requests someone: "I need to speak with Bob"
  2. Press the programmed button: automatically places the caller on hold and dials the Voice Agents
  3. Tell the AI: "Find Bob" or "Is Bob available?"
  4. AI handles screening: Calls Bob, asks if he wants to accept, gets response
  5. Automatic result: Call connects to Bob, or agent is notified Bob is busy

Almost all VoIP desk phones support programmable buttons that can put an active call on hold and dial the extension for the Voice Agents. 

Benefits

The benefits of Gemini Attended Call Transfer include:

  • One-Button operation: manage everything with a single button
  • Increased efficiency: no manual dialing or waiting for colleagues to answer
  • Professional screening: AI provides context (caller name)
  • Increased productivity: employees can decline calls when busy or in meetings
  • Reduced hold times: faster resolution for callers
  • Universal: for anyone with a desk phone, including assistants, receptionists, team members, etc. 

Detailed configuration and usage instructions are available in the Voice Agents JS Example – Gemini Attended Transfer documentation

At Vodia, we’ve spent more than a decade and a half developing a cloud phone system that supercharges business communication. We also regularly cast a wide net to make sure we integrate with the world’s best third-party business software. Find out more about what makes us the phone system of choice for organizations around the world, email us at sales@vodia.com, or call +1 (617) 861-3490 (United States), +61 2 7201 0788 (APAC), or +49 30 555 78749 (Europe).

*Google and Gemini are trademarks of Google LLC

Latest Articles

View All

Cisco IP Phone Series 6800, 7800 and 8800 with the Vodia PBX

Cisco IP Phone Series 6800, 7800, and 8800 devices running Multiplatform (MPP / 3PCC) firmware can be used with the Vodia PBX in SIP-based environments. Supported models span entry-level, mid-range, and advanced devices commonly deployed in enterprise and service provider scenarios. Cisco-provided MPP firmware is used, with firmware versions and upgrades managed through the PBX after initial onboarding, supporting both on-premises and cloud deployments.

February 19, 2026

Sonic: Music on Hold and the Vodia PBX

Music on Hold plays an important role in how callers experience wait times and perceive service quality. With Vodia PBX Version 70, we’ve enhanced Music on Hold to deliver neutral, calming, high-quality audio that reassures callers while they wait. These improvements, combined with flexible streaming options, emergency messaging, and full support for cloud and on-premises multi-tenant environments, help businesses reduce dropped calls and create a more positive caller experience before an agent ever answers.

February 17, 2026

Open Source PBX vs Commercial PBX: What You’re Really Managing

Organizations often start with an open source PBX for flexibility, but as systems move from initial setup to daily operations, the real cost becomes management, maintenance, and long-term reliability. This article explores the difference between building a PBX stack from frameworks and running a commercial, integrated PBX platform, focusing on operational complexity, security responsibility, upgrades, and ongoing maintenance. It explains how a purpose-built PBX shifts the burden from continuous engineering to stable operation, helping teams prioritize clarity, control, and scalability as requirements grow.

February 12, 2026