Skip to main content

Documentation Index

Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Back to list of all release notes This document provides information on the latest feature updates and enhancements introduced in the Voice Gateway of AI for Service (XO) v11.x releases. For previous updates, see release notes of 2025.

​
v11.24.1 May 09, 2026

This update includes only bug fixes.

​
v11.24.0 April 25, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

ASR and TTS

Playback Status for Background TTS Streaming

Playback status is now captured during background TTS streaming to determine completion and prevent interruptions in call flows. This ensures accurate execution of subsequent call actions across Deepgram, ElevenLabs, and custom TTS vendors.

Word-Level Timestamps for ASR Transcriptions

Word-level timestamps for ASR-generated transcriptions are now stored and made available for downstream modules and use cases, supporting features such as quality analysis and detailed conversation insights. Timestamps are captured and persisted in their native format for flexible consumption.

ASR Dropdown Support for Deepgram Flux

The Deepgram Flux option now appears in the ASR dropdown alongside Deepgram in the Start Flow configuration. Selecting it applies default values for deepgramEotThreshold and deepgramEotTimeoutMs in the session configuration. User-defined values override defaults when explicitly configured. Learn more→

Call Transcription

Transcript Enhancement for IVR Prompts and DTMF Capture

IVR prompts played during waiting and callback flows-including Initial, Transfer, Periodic, Callback, Voicemail, and Chat Deflection messages-are now recorded in the interaction transcript along with all user DTMF inputs. DTMF entries appear in the same format as Automation interactions and follow the correct chronological sequence. Callback scenarios include both the user’s DTMF input and confirmation messages without data loss.

Transcription Language Selection for Manual Outbound Calls

Agents can select a transcription language during manual outbound calls via a dropdown that includes enabled languages from user attributes, plus an Autodetect option. If no selection is made, the bot language is applied by default. Any language selected will be saved for future calls, with the option to modify it before each call. Learn more→

Call Recording

Video Call Recording for Chat-Escalated Interactions

Agents can manually start, pause, resume, and stop video call recording with customer consent. The recording captures video, audio, and screen share, with clear indicators shown to both the agent and the customer. Recordings stop when the call ends, process asynchronously, and are available as download-only files with defined retention (of voice call recordings) and error handling. Learn more→

​
v11.23.1 April 11, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

Text to Speech

Background TTS Streaming Enhancements

  • TTSOptions Support: ttsOptions is now supported during background TTS streaming, allowing dynamic voice and language changes. This applies across Message, Entity, and Agent nodes without impacting streaming behavior, and excludes TTS text streaming to avoid latency from connection re-establishment.
  • Playback Status Support: Playback status is now captured during background TTS streaming to accurately detect completion, ensuring correct handling of prompts, hang-up flows, and no-input scenarios. Currently, Microsoft ASR and Sarvam (Custom) are supported, with extensibility for other providers.

​
v11.23.0 March 28, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

ASR and TTS

IST Generative TTS: Text Streaming Support

IST Generative TTS now supports text streaming, configurable via call control parameters. Enable streaming at the agent node level to reduce latency and improve response delivery. SSML is supported.

Integrations

Grok Voice Models for Real-Time Voice

The Platform now supports the Grok Voice (xAI) model for real-time voice interactions alongside the existing providers. Upon configuration, it enables real-time audio streaming, response handling, and logging. It maintains backward compatibility with the existing providers.

​
v11.22.1 March 14, 2026

This update includes only bug fixes.

​
v11.22.0 February 28, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

ASR and TTS

Google Cloud TTS Streaming Support

Google Cloud Text-to-Speech now supports both audio and text streaming. Audio streaming is enabled by default, while text streaming requires the TTS Streaming and Model Response Streaming flags. Streaming works across standard flows, Agent Node, and Agentic App use cases, with seamless playback, defined latency thresholds, fallback handling, and full backward compatibility. Support applies only to HD (Chirp) voices.

Azure TTS Text Streaming Support in Voice Gateway

Voice Gateway now supports Azure TTS text streaming, enabling progressive speech synthesis for real-time LLM responses. Streaming operates over WebSocket with seamless audio continuity, validation controls, and graceful fallback to non-streaming mode when needed.

Deepgram ASR: Flux Model Integration

Voice Gateway now supports the Deepgram Flux ASR model, delivering improved turn detection, lower latency, and better transcription quality. The ASR selection dropdown includes Deepgram ASR-Flux, supporting English across all accents.

Agentic Apps

Remove Tool-Call Audio in Agentic App

The system no longer plays default music when the Agentic App makes a tool call using real-time voice APIs. The platform remains silent during tool execution until the bot responds, preventing audio overlap—even if the response is delayed.

Configuration

SIP Trunk Configuration: Same DID Handling

If a SIP trunk uses the same DID with a different IP/FQDN, the system allows it across different accounts or apps, but prompts for confirmation within the same account and app. If both the DID and IP/FQDN match an existing entry, the system blocks creation and displays an error message.

​
v11.21.1 January 31, 2026

This update includes only bug fixes.

​
v11.21.0 January 17, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

ASR and TTS

TTS Streaming at Start Flow Level

TTS Streaming can be configured at the start flow level to reduce voice response latency. The platform maintains a persistent streaming connection throughout the call and adapts playback based on the model’s response streaming behavior.

Continuous Gather at Start Flow Level

Provided a Continuous Gather option at the start flow when TTS streaming is enabled. Caller input is captured continuously to reduce latency and support agentic voice interactions, without altering default behavior unless configured.

Model Selection for ASR and TTS Providers

The platform now permits model selection for ASR and TTS providers directly from the app-level and Start Flow-level UIs. The selected model is consistently applied across design-time and runtime voice scenarios, including interactions, transcriptions, and monitoring, without requiring call-control parameters.

TTS Providers: Required Language Support

The platform ensures that all natively supported TTS providers offer support for required languages wherever the vendor supports them. This applies to AWS Amazon Polly, Google, Microsoft Azure, ElevenLabs, OpenAI TTS, Deepgram, and similar integrations. The required languages include English, Japanese, Spanish, German, Arabic, French, Hindi, and Filipino.