Hi, I have an assistant with id

3f15c5a7-7f67-497b-bb67-4b680592703f

and that I have configured to use Scribe v2 Realtime model, which is supposed to have 150ms latency. However, on the estimation bar I see it as 800ms. Why? https://cdn.discordapp.com/attachments/1464604256790122671/1464604256979124433/image.png?ex=69761281&is=6974c101&hm=9918d33d571422edcf0e6b48e800292b065965c2d774787930fbd864f4e50fb7&

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

To investigate the latency discrepancy, review the actual transcriber latency for your calls in the Vapi dashboard: 1. Go to Observe > Call Logs in your [dashboard](https://dashboard.vapi.ai/). 2. Select a recent call and check the

transcriberLatencyAverage

metric to see the real performance. This will help you determine if the Scribe v2 Realtime model is performing as expected or if there is a configuration issue causing the higher estimate. Reference: [Vapi Debugging Guide](https://docs.vapi.ai/debugging) Source: - [Vapi Debugging Guide](https://docs.vapi.ai/debugging)

Note, here is the article advertising it should have 150ms of latency - https://elevenlabs.io/realtime-speech-to-text

This is just an estimate. There appears to be an issue where the Eleven Labs transcriber shows 800ms consistently, but this does not affect the actual latency. Please test this on a real call and let me know how the latency feels. We also provide performance metrics for real latency, which you can use for comparison.