I’m currently working on analyzing how fast the bot responds to user inputs during calls. API used: https://api.vapi.ai/call In the API response, I see a messages field that includes transcripts with time and endTime values. I assumed I could measure the bot’s response time by calculating endTime - time, where: time refers to when the bot starts speaking endTime refers to when the user finishes speaking However, the values I'm seeing don’t seem to match real-world timings or expected durations — they either appear too short or inconsistent. Could you please clarify: What exactly do the time and endTime fields represent in the messages array? Is there a recommended way to measure the time it takes for the bot to respond after a user input? Is there any other field or approach you’d suggest to get accurate response time data for user-bot exchanges? Thanks in advance for your help!

Hi CHUzLEE, To measure the bot’s response time effectively, you can use the timestamps within the

messages

field of the Vapi API response. However, it's important to clarify the purpose of each timestamp: - `time`: This indicates when the message instance was created, which could be either the start of the bot’s response or the user input being captured. - `endTime`: This is typically associated with the duration of the bot's response. For calculating the bot's response time, consider measuring from the time the user finishes speaking (end of their message) to the start of the bot's response. This may not directly be

endTime - time

as you mentioned. If there seems to be a discrepancy, ensure you are accounting for all contributing factors like API lag or network delays. For further assistance, it may help to check call logs for a detailed sequence of events, which can be accessed via your Vapi dashboard ([Debugging voice agents](https://docs.vapi.ai/debugging)).

" consider measuring from the time the user finishes speaking (end of their message) to the start of the bot's response." I did this. However the data it gave does not present the true values.

Hi, First off, we want to sincerely apologize for the delay in getting back to you. We understand how frustrating it is to wait - especially when you're counting on us - and we owe you a clear explanation of what’s been happening and how we’re addressing it. Over the past few weeks, we've seen a significant increase in support requests. While this reflects exciting growth, it has also stretched our small team and exposed some real challenges in scaling our support operations. To improve your experience, we’ve taken a step back to reassess our approach. Here’s what we’re implementing: - Smarter Support Through Automation: We’re investing in our AI support systems to help you resolve issues more efficiently. Soon, our support bot will offer expanded capabilities, making it easier to access accurate, instant help—particularly for common or repetitive queries. - Expanding the Support Team: To meet growing demand, we’re adding 2–3 new team members focused on managing support volume and improving response times. - Prioritized SLAs for High-Usage Accounts: We’re introducing service level improvements for users who are growing with us: - Accounts with usage over 1,000 minutes/month will receive prioritized support. - For all general inquiries, we’re establishing a standardized 48-hour response time. We’re confident these steps will lead to faster, more reliable support and help us better serve you as you grow with us. Also, in case you still need help with this ongoing ticket, do let us know, and we will help you get this resolved as soon as possible. Thank you for your continued patience and for being part of our journey. Warm regards, Vapi Team