I created a new squad with 2 very simple assistants to test the routing (a few lines of prompt, no more). I add an existing assistant in the squad (31 lines of prompts, nothing crazy). I don't even connect it to another agent: when I start the conversation through a web call, the agents speak extremely slowly, I can't even understand what it says. The STT when I speak is also slow and completely wrong ("I would like to know more about your services" transcribed as "It's a fun event." ??!!). I tried by removing or addind agents, creating a new squad, refreshing the browser, the problem remains. As soon as I have more than 2 agents in the squad, the problem occurs. I'm using: Chrome 142.0.7444.176 Windows 11

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

Try updating your squad's transcriber to use Deepgram Nova 2 or Nova 3 for faster and more accurate speech-to-text. Here's an example configuration snippet:

json
"transcriber": {
  "provider": "deepgram",
  "model": "nova-2",
  "language": "multi"
}

Apply this in your assistant or squad settings and test again—this often resolves slow and inaccurate STT/TTS issues when multiple assistants are present (according to the documentation I have found: https://docs.vapi.ai/customization/multilingual). Source: - [Multilingual Support Documentation](https://docs.vapi.ai/customization/multilingual)

All the agents use Deepgram Nova-3. They all work individually. As I said: it's when you have more than 2 of them in one squad that it stops working and becomes messy.

Hi Elodie T., If you're setting up a call system and experiencing issues, consider the following: 1. **Assistant Configuration**: Ensure the assistant configurations, including models, voice providers, and server settings, are properly set up. Refer to the [changelog](https://docs.vapi.ai/changelog/2024/10/13) for details about configuring voice models and servers. 2. **Squad Setup**: Use the provided examples in the [clinic triage and scheduling squad document](https://docs.vapi.ai/squads/examples/clinic-triage-scheduling) to guide the setup of multi-assistant squads, preserving context and managing transfers effectively. 3. **Voice Speed Issue in Squads**: If an assistant within a squad speaks slowly, ensure all voice providers match in sampling rate (44100 Hz) as outlined in the related threads. 4. **Call Timeout and Max Duration**: Adjust the call duration settings if necessary, as the maximum duration is now up to 43,200 seconds, according to the [October 19, 2024, changelog](https://docs.vapi.ai/changelog/2024/10/19). Implement these configurations to optimize assistant performance and transfer procedures.