# July, 2026 - Updated on Jul 16, 2026 - Published on Jul 16, 2026 - 3 minute(s) read ### Introduction This month's updates introduce new features that make it easier for Sanas app users to **test and troubleshoot their audio experience**, while delivering significant enhancements to **Speech Intelligence** with more customizable call insights, improved call quality detection, faster dashboard performance, more resilient post-call processing, and a more intuitive live tracking experience. ### What’s New - [**Hear Your Voice**](https://help.sanas.ai/portalv3/docs/july-2026#hear-your-voice-inapp-feature) is a new in-app feature that lets users record and instantly preview how they'll sound through the active Sanas pipeline, with access controlled by a toggle in the Sanas Portal. - [**Synthesis Indicators**](https://help.sanas.ai/portalv3/docs/july-2026#s) add clear visual status indicators in the Sanas app, helping users quickly identify if audio synthesis isn't running and troubleshoot common issues without checking logs or contacting support. - **Speech Intelligence Enhancements** - [**Customizable Call Details**](https://help.sanas.ai/portalv3/docs/july-2026#call-details-page) now support group-specific prompt configurations for **Action Items** and **Discussion Points**, enabling customizable account-level formats in the Sanas Portal without requiring code changes. - For [**Call Quality**](https://help.sanas.ai/portalv3/docs/july-2026#call-quality-enhancement-for-speech-intelligence-in-the-app), we introduce **five new inbound call-quality alert rules** and **improved backend block patterns** to reduce false positives, delivering more accurate Speech Intelligence alerts throughout. - [**Dashboard** and **Call History**](https://help.sanas.ai/portalv3/docs/july-2026#dashboard-and-call-history-performance-for-speech-intelligence-in-the-app) have been improved with faster dashboard and call history loading, plus optimized caching for Call Details to deliver quicker access to summaries, action items, and discussion points. - Improved [**Post-Call LLM Reliability**](https://help.sanas.ai/portalv3/docs/july-2026#improved-reliability-for-post-for-speech-intelligence) adds OpenAI as a fallback provider when the primary Anthropic service is unavailable, ensuring more resilient and reliable post-call processing. - Interactive [**Live Tracking**](https://help.sanas.ai/portalv3/docs/july-2026#improved-live-tracking-for-speech-intelligence) now offers improved usability through refined alert layouts, smoother call drill-downs, longer agent visibility after calls, and color-coded call duration timers for quicker monitoring. --- ### Hear Your Voice In-App Feature **Sanas Desktop App version**: **5.7.4 (Self-Serve)** and **5.7.5 (Direct-CX),** and later - A new in-app utility that lets app users record a short audio clip and play it back through the active Sanas pipeline. This gives users an immediate preview of how they will sound to others during meetings, without needing to schedule a test call. - **How it works?** - Can be enabled by account admins through a toggle in the Sanas Portal. - **Sanas Portal** → **Settings** → **Configuration** → **Desktop Application** → **Application Settings**. > Note: This release goes together with new Sanas Portal version 1.11.0, and above. --- ### Synthesis Indicators in the Sanas App **Sanas Desktop App version**: **5.7.4 (Self-Serve)** and **5.7.5 (Direct-CX),** and later - The Sanas app now displays clear visual indicators of the audio synthesis state, available to all app users by default. When synthesis is not running, app users can immediately see why, making issues easier to diagnose without checking logs or contacting support. - Currently handled states include: - Audio device failures - Model load errors - Synthesis is being explicitly turned off by the user - The Sanas device is not configured as the default device --- ### Call Details Section Enhancement for Speech Intelligence **Sanas Speech Intelligence model version**: **1.2.0** and above - **Action Items** and **Discussion Points** in Call Details of the Sanas portal now support group-specific prompt configurations, allowing each account to define its own format without requiring a code change. - **How it works?** - **Backend:** The summary schema has been updated to support flexible structures and has added v2 keys for `actionItems` and `discussionPoints`. - **In the Sanas Portal:** Added generic rendering in Call Details to display any prompt-defined structure. > Note: This release goes together with new Sanas Portal version 1.9.7, and above. --- ### Call Quality Enhancement for Speech Intelligence **Sanas Speech Intelligence model version**: **1.2.0** and above - **New Alert Rules** - Seeded five new call-quality regex-based alert rules in the Portal Speech Intelligence configuration: - Communication Clarity - Follow-up Failure - Excessive Hold Time - Resolution Failure - Perceived Knowledge Gap > Note: All five rules are active for inbound calls on the Sanas account. Also, this release goes together with the new Sanas Portal version 1.9.7, and above. - **Block Patterns** - Added second-pass block patterns to the SCI backend for all call-quality rules to reduce false positives during post-call reconciliation. --- ### Dashboard and Call History Performance for Speech Intelligence **Sanas Speech Intelligence model version**: **1.2.0** and above - Improved **dashboard API response times** by implementing ClickHouse connection pooling and parallelizing queries for alerts and call history. - **Call Details payloads**—including summaries, action items, and discussion points—are now cached in Redis and pre-warmed when call summaries are generated, enabling faster repeat views. > Note: This release goes together with the new Sanas Portal version 1.9.7, and above. --- ### Improved Post-Call LLM Reliability for Speech Intelligence **Sanas Speech Intelligence model version**: **1.2.0** and above - Added OpenAI as a fallback provider when the primary Anthropic service is unavailable, improving the resilience of the post-call processing pipeline. --- ### Improved Interactive Live Tracking for Speech Intelligence **Sanas Speech Intelligence model version**: **1.2.0** and above - **Compliance Statistics**: Removed the double-scroll behavior in the call drill-down modal. - **DOB Validation Alerts**: Refined the alert details layout by reducing the oversized text area and aligning the font and colors with the rest of the page. - **Roster Grid**: Agent tiles now remain visible for 20 seconds after a call ends, up from 5 seconds. - **Call Duration Timer**: Added color coding—green for calls under 90 seconds and red for calls lasting 90 seconds or longer. > Note: This release goes together with the new Sanas Portal version 1.9.7, and above. --- ### Support **Need help?** Get in touch with our [Support Team](mailto:support@sanas.ai) for assistance.