Latency 3 times longer than the estimate
# support
f
Example of call: 03b7b32e-ca04-47a2-ba3f-e6687cd87ae1 I've been using Vapi for a few months now and I've never managed to get anywhere near the estimate (lots of different combinations with the different providers). There's a huge difference between the estimate and the true latency. This latency has a huge impact on the user experience and the validation of a product. How do you explain this? Also, could coding the solution and hosting it on a fast cloud server in France reduce latency? Thanks!
v
message has been deleted
@Florian I'm sorry to hear that you're experiencing latency issues with Vapi. We pride ourselves on having low latency and high reliability, so it's important for us to address this concern. There could be several factors contributing to the difference between the estimated and actual latency you're experiencing: 1. **Network Conditions**: The path your data takes through the internet can affect latency. Network congestion, routing paths, and the distance data must travel can all play a role. 2. **Integration Complexity**: The way Vapi is integrated into your application can also impact latency. The efficiency of the code and the number of intermediary services can add delay. 3. **Provider Performance**: Different voice providers may have varying performance characteristics, and their infrastructure might affect latency. 4. **Client-Side Issues**: The devices and networks used by your end-users can also contribute to perceived latency. Hosting your solution on a fast cloud server in France, or closer to your user base, could potentially reduce latency, especially if network distance is a contributing factor. Cloud servers often have high-speed connections and can process requests quickly, which might help mitigate latency issues. To better assist you, we would need to look into the specific details of your use case. If you could provide more information about the scenarios where you're seeing high latency, we can investigate further and provide more tailored advice. In the meantime, if there's anything specific you would like us to check or any further assistance you need, please let us know!
You can continue this conversation by mentioning me in the message.
s
It is because you are in Europe and our servers are in US-WEST + Yesterday, OpenAI was facing some degradation issue.
f
Hi @Sahil It's like this since I've started using Vapi (2/3 months ago). The issue isn't related to OpenAI.
s
can you send me your assistant id?
f
a245a1b2-63ef-4258-bb2e-7edb1119e1e2
j
I thought they was in US east this whole time
l
Hi @Florian i have the same problem, i'm in Europe as well (italy) and it seems like we still have to wait to have a decent Agent. As voice provider in Vapy we have only 11Labs with the multilingual model right?
s
Nope, our servers are in US-WEST