Williham
03/13/2025, 5:03 PMVapi Support Bot
03/13/2025, 5:05 PMstartSpeakingPlan.smartEndpointingEnabled
must be a boolean value (true or false).
Here's how to fix this:
1. Make sure you're setting smartEndpointingEnabled
as a boolean value:
json
"startSpeakingPlan": {
"waitSeconds": 0.8,
"smartEndpointingEnabled": false // or true
}
About Smart Endpointing:
This feature helps detect when a user has truly finished speaking, rather than just pausing briefly. It's [off by default](https://docs.vapi.ai/customization/speech-configuration) and works best with English transcriptions.
Recommendations:
- Set to false
if you're using non-English transcriptions
- A common wait time setting is 0.8 seconds
- For English transcriptions, you can set it to true
if accurate transcription is confirmed
Example configuration:
json
{
"startSpeakingPlan": {
"waitSeconds": 0.8,
"smartEndpointingEnabled": false
}
}
Let me know if you need any further help with this! 😊
Sources:
- [VAPI AI Documentation](https://docs.vapi.ai/customization/speech-configuration)
- [Discord Channel](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1334385998423130174)Williham
03/13/2025, 10:33 PM