We're thrilled to share some exciting new features and updates on the platform. Here’s what’s new:

AI QA automatically reviews your calls and provides crucial feedback 24/7.
With AI QA, you can:
→ Surfaces patterns in your calls: Find and fix systematic issues without getting stuck on one-off bad calls.
→ Track Resolution rates across every call: Transfer rate, disconnect reasons, repeat contact patterns — by agent, call type, time period.
→ Catch what humans can't: Hallucination rate, sentiment shifts, tool accuracy — measured automatically across every call.
First 100 minutes of analysis is free.

With Alerting you can set triggers that alert you the moment something goes wrong with your agents.
Alerting lets you:
→ Know when an agent burns $100 in minutes, success rate hits 0%, sentiment drops 20% and more.
→ Delivered via email or integrate into your existing tools via webhook
→ Smart thresholds so you only get alerted when it actually matters
It only takes 2 minutes to set up your first alert.

Search between any node in seconds using the search box or cmd/cntrl+F to review and audit large flows faster.
Export Call History — Export any of your agents' entire call history with URL's.
Voice API — Add-voice, search-voice, and clone-voice APIs are now exposed through the SDK.
Custom Transcription Config - You can now choose between optimizing for accuracy or latency by changing the number of endpoints used
HubSpot Integration — Retell is now available through the HubSpot Marketplace.
Auto IVR Hangup — You now have an option to automatically hang up if your agent encounters an IVR system.
Auto transcription fallback — If Deepgram or Azure has an outage, we seamlessly switch to the other provider without dropping audio, even mid-call.
Voice Emotion Control — Cartesia Sonic-3 models now support Happy, Surprised, Sympathetic, and Calm. MiniMax voice models now support Happy, Surprised, and Calm
Concurrency Blast — Allows up to the lower of 3x your concurrency limit or 300 additional concurrent calls. $0.1/minute for burst usage.