Release 2026.15 of Cognigy introduces the new Genesys Audio Connector integration, alongside native support for GPT-5.6 - OpenAI's latest frontier model family.
Future-Proof Voice Connectivity with Genesys Cloud
Cognigy Voice Gateway now supports the Genesys Audio Connector (beta), a new integration that connects Genesys Cloud to Voice Gateway using the AudioHook protocol over WebSocket.
Until now, connecting Genesys Cloud to Cognigy Voice Gateway meant relying on SIP calling. The Genesys Audio Connector removes that dependency, letting Genesys Cloud customers integrate with Cognigy over a native WebSocket-based audio stream instead. That means less infrastructure to configure and maintain, and a more direct path from Genesys Cloud into your AI Agents.
Key advantages include:
- Continuity for Genesys customers: Future-proof your AI Agent operations with a native integration option that supports evolving Genesys Cloud capabilities.
- Minimal setup: The connector uses a predefined carrier template in the Voice Gateway interface. Required settings are preconfigured, reducing setup steps compared to a standard carrier.
Keeping Pace with the Frontier: GPT-5.6 Support
The latest release also adds native support for the GPT-5.6 model family — gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna — OpenAI's newest model generation, available through both Azure OpenAI and OpenAI connections and callable via the Responses API request type.
GPT-5.6 spans three tiers, giving you a model for every AI Agent use case:
-
Sol is the flagship, built for the most demanding reasoning, coding, and long-running agentic tasks
-
Terra is a balanced option for everyday work with performance competitive with the prior generation at a lower cost
-
Luna is the fastest and most cost-efficient tier, suited to high-volume, latency-sensitive interactions like simple lookups or intent handling.
Across the family, OpenAI reports stronger performance per token — meaning more useful work per request, which can translate into lower LLM costs at scale without sacrificing response quality.

Other Improvements
Cognigy.AI
- Improved the localization logic in the Simulator. Now, both AI Agent and simulated user interact in the selected locale language instead of defaulting to English
- Updated the Conversation Counter in Admin Center and Management UI to use the v3 pre-aggregated Conversation Counter API. Conversation counts are now calculated overnight and available up to the previous day, with data available from 2025 onward
- Improved attachment handling for Genesys Open Messaging integrations by sending user chat attachments with the correct media types in Webchat v3 and WhatsApp
- Added Script ID visibility for the NiCE CXone (Integrated) handover provider. Users can now view and copy the Script ID to distinguish between different configured scripts
- Reordered the settings on the Project Settings page to reflect priority order
Voice Gateway
- Removed the feature flag for Call Failover in the Set Session Config Node. The feature is now generally available.
- Improved handling of unwanted SIP traffic
- Improved endpoint validation for the call-recording upload path
Webchat
- Removed the option to create new Webchat v2 Endpoints from the Endpoints page and the Cognigy.AI API. Existing Webchat v2 Endpoints are unaffected and continue to work
Agent Copilot
- Introduced expanded JWT authentication options for Agent Copilot. Now, you can configure symmetric or asymmetric JWT verification in the Endpoint settings, including authentication through shared keys or public keys and JWKS endpoints for improved security and key rotation support.