Robert Simons
04/11/2025, 7:03 PMVapi Support Bot
04/11/2025, 7:05 PMsmartEndpointingEnabled
to false
in your assistant configuration [via the UPDATE /assistant/:id API](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1332286268805087272).
2. **Adjust Deepgram's Endpointing Settings**:
Try setting Deepgram's endpointing to 300ms [in your configuration](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1332286268805087272).
3. **Configure startSpeakingPlan and Transcriber Settings**:
Update your configuration with these settings:
json
"startSpeakingPlan": {
"waitSeconds": 0.8,
"smartEndpointingEnabled": false
},
"transcriber": {
"model": "nova-2-phonecall",
"provider": "deepgram",
"endpointing": 300
}
[as suggested in this thread](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1329414710583627796).
4. **Adjust numWordsToInterruptAssistant and maxDurationSeconds**:
Try updating numWordsToInterruptAssistant
to 5 and maxDurationSeconds
to 10 in your settings [via the VAPI dashboard](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1334027136305991750).
5. **Check for Hidden Configuration Differences**:
Even though your assistants have "the same settings," there might be underlying default values that differ. Use the GET /assistant/:id
endpoint to get the full configuration of both assistants and compare them thoroughly.
Would you like me to provide more specific guidance on implementing any of these solutions?
Sources:Vapi Support Bot
04/11/2025, 7:05 PMKings Big
04/11/2025, 7:14 PMRobert Simons
04/11/2025, 7:22 PMKings Big
04/11/2025, 10:10 PMstartSpeakingPlan": {
"waitSeconds": 0.6,
"smartEndpointingPlan": {
"provider": "livekit",
"waitFunction": "50 + 200 * x"
}
}
Kings_big💫
04/12/2025, 4:35 AMKings Big
04/14/2025, 6:06 AM