Hey Vapi team, hoping someone can offer insight or suggestions! I’m running a voice assistant for my company, and I’m struggling to get the right balance between latency and patience when callers give complex responses—especially with addresses (e.g., “892 Southwest 14th Street, Miramar 33022”). The biggest problem is that Jamie often cuts off callers before they’re finished, even when I set the pause detection (“onNumberSeconds”, “onPunctuationSeconds”, “onNoPunctuationSeconds”) to the max (3 seconds). What I’ve tried so far: Set all endpointing parameters to 3 seconds (the max in the Vapi UI) Tested with Deepgram Nova 2, Deepgram Nova 3, and OpenAI GPT-4o Transcribe models Deepgram is much faster (low latency, ~750ms), but still cuts off callers on long responses OpenAI GPT-4o is more patient, but the latency jumps to ~1500ms, which makes the experience feel sluggish and robotic What I’d like to know: Is there a way to push the endpointing/pause thresholds even higher (beyond 3 seconds) for certain questions or globally—maybe via API, advanced config, or feature request? (Even a few extra seconds would help with addresses.) Is there any way to tune or override the startSpeakingPlan and stopSpeakingPlan beyond what’s available in the UI, to better handle “chunky” user responses (e.g., when callers pause between house number, street, and city)? Has anyone found a workaround to keep latency low but make the bot “wait longer” before responding, especially for multi-part responses like addresses or emails? Is there a recommended combo of model + settings that works best for real-world phone calls where users naturally pause or spell things out? I want to deliver a natural, patient, human-like experience—but I keep hitting the wall of either cut-off responses (if latency is low) or robotic/slow responses (if patience is high). Any advice, advanced tricks, or suggestions would be hugely appreciated!

You can override the default endpointing/pause thresholds by configuring the

startSpeakingPlan

via the API, allowing values higher than the UI limit. For example, to make the bot wait longer before responding, try:

json
"startSpeakingPlan": {
  "waitSeconds": 1.5,
  "transcriptionEndpointingPlan": {
    "onPunctuationSeconds": 4,
    "onNoPunctuationSeconds": 5,
    "onNumberSeconds": 4
  }
}

Set these values in your assistant config via the API to experiment with longer pauses for complex responses like addresses. Test for side effects on latency and user experience, as provider/model support for higher values may vary. [See more in the docs](https://docs.vapi.ai/customization/speech-configuration) Source: - [Speech configuration](https://docs.vapi.ai/customization/speech-configuration)

Thanks for the quick response! That helps clarify a lot. Just to dig a little deeper— If you were in my shoes, trying to optimize for the least possible cut-offs (especially when people are giving addresses, phone numbers, etc.), would you recommend: Relying on Smart Endpointing, Manually setting higher thresholds for punctuation, numbers, and silence, Or is there another approach that tends to work best for these real-world business calls? Also, out of the available transcriber models (Deepgram Nova 2, Deepgram Nova 3, OpenAI GPT-4o Transcribe, Mini, etc.), do you find any are more reliable for natural turn-taking and not missing parts of numbers or addresses? Finally, is there any way to get beyond the current parameter limits via API, or is that maxed out for now? Just want to make sure I’m not missing something obvious. Appreciate the help!

Use Vapi’s API to extend pause thresholds beyond 3 seconds with startSpeakingPlan.waitSeconds and smartEndpointing: "livekit", while tuning stopSpeakingPlan to prevent cutoffs, balancing low latency with more natural, patient responses..

Hey [Saltlife Kid](https://app.plain.com/workspace/w_01HYEQ5FKPH8CPX2MS608B6S51/customers/c_01JSF7GC75CNXNZB0KEGZ4R247/)**, checking if this is resolved/solved for you?**