Understanding Lindy Call Icon & Delays in Twilio Integration

Paulo C. · 2025-06-23 17:05:03.301686+00

Hi Lindy team! I have a phone call step using Twilio in some Lindies, and I noticed that when this step is triggered, the "tasks" page shows the Lindy call icon. Does that mean that the call is still being made through the action "Make Phone Call" of “Lindy Phone", instead of the action "Make Phone Call" of Twilio, and it’s just using the Twilio-registered phone number? We’ve been experiencing a bit of a delay in responses during the calls. Do you have any suggestions on how to reduce that?

Understanding Lindy Call Icon & Delays in Twilio Integration | Lindy Community

6 comments

· Sorted by Oldest

Alon J.
·
·
Hey Paulo! Hmmm - do you mind sending the task URL, so I can see what you're referring to? Happy to help How to share your Lindy task URL: 1. Click your Lindy agent → click “tasks” 2. Find the task you need help with 3. Click the specific task (you should see the full execution) 4. Copy that page URL from your browser 5. Paste the URL in your support request
Paulo C.
·
·
Hi Alon! Sorry for taking so long to respond. I missed your response. Here's the link: https://chat.lindy.ai/griffin-morriss-workspace/lindy/mkt-call-leads-low-score-v2-682cc31545551db50380abc2/tasks?task=685ee1169646483e629d0885
Alon J.
·
·
Hey Paulo -- Apologies about the delay! Ah, yeah! Twilio is only used to initiate and route the call through the Twilio number, but you're seeing the Lindy call icon on the Tasks page since the call is still being routed through Lindy's call system. How bad is the delay? I'd suggest upping your models that are specifically for calling. I noticed you're using Gemini Flash 2.0 in your AI Agent that responds after the call picks up - You can try using Gemini Flash 2.5 (or GPT-4 Turbo, or Claude 4 Sonnet), which may help! Let me know how that goes :)
Paulo C.
·
·
Thanks, Alon! I'll give it a try!
Paulo C.
·
·
Actually, I realized that I'm having this issues with a similar flow that's already using Claude 4 Sonnet for the calls. When the call starts, the first delay after the person says "hi" can be from 3 or 4 seconds sometimes. Since the person don't realize that they're talking to an AI at first, they say something like "hey is anyone there?" because they don't get an instant answer because of the delay and then the AI have to recalculate what it was going to say for the first "hi" that the person said. This may cause the AI to "glitch", because the text it was supposed to say appears on the transcriptions in the tasks but the AI don't actually say all of that to the person on the call
Alon J.
·
·
Hmmm -- Are you able to send me the task URL for that specific example? I'll get my team to look into why that's happening

Alon J.
·
·
Hey Paulo! Hmmm - do you mind sending the task URL, so I can see what you're referring to? Happy to help How to share your Lindy task URL: 1. Click your Lindy agent → click “tasks” 2. Find the task you need help with 3. Click the specific task (you should see the full execution) 4. Copy that page URL from your browser 5. Paste the URL in your support request
Paulo C.
·
·
Hi Alon! Sorry for taking so long to respond. I missed your response. Here's the link: https://chat.lindy.ai/griffin-morriss-workspace/lindy/mkt-call-leads-low-score-v2-682cc31545551db50380abc2/tasks?task=685ee1169646483e629d0885
Alon J.
·
·
Hey Paulo -- Apologies about the delay! Ah, yeah! Twilio is only used to initiate and route the call through the Twilio number, but you're seeing the Lindy call icon on the Tasks page since the call is still being routed through Lindy's call system. How bad is the delay? I'd suggest upping your models that are specifically for calling. I noticed you're using Gemini Flash 2.0 in your AI Agent that responds after the call picks up - You can try using Gemini Flash 2.5 (or GPT-4 Turbo, or Claude 4 Sonnet), which may help! Let me know how that goes :)
Paulo C.
·
·
Thanks, Alon! I'll give it a try!
Paulo C.
·
·
Actually, I realized that I'm having this issues with a similar flow that's already using Claude 4 Sonnet for the calls. When the call starts, the first delay after the person says "hi" can be from 3 or 4 seconds sometimes. Since the person don't realize that they're talking to an AI at first, they say something like "hey is anyone there?" because they don't get an instant answer because of the delay and then the AI have to recalculate what it was going to say for the first "hi" that the person said. This may cause the AI to "glitch", because the text it was supposed to say appears on the transcriptions in the tasks but the AI don't actually say all of that to the person on the call
Alon J.
·
·
Hmmm -- Are you able to send me the task URL for that specific example? I'll get my team to look into why that's happening