Issue enabling LiveKit turn based detection
# support
@Shubham Bajaj
v
Hi there! I see you're having an issue with the error "startSpeakingPlan.smartEndpointingEnabled must be a boolean value" when trying to enable turn-based detection in LiveKit. This error occurs because the
smartEndpointingEnabled
parameter specifically requires a boolean value (true or false), not a string or any other data type. Here's how to fix it: 1. Make sure you're setting
smartEndpointingEnabled
as a boolean value:
Copy code
json
   "startSpeakingPlan": {
     "waitSeconds": 0.4,
     "smartEndpointingEnabled": true
   }
2. If you're using a UI to configure this, ensure you're selecting the boolean option rather than entering text. 3. Note that smart endpointing is only functional for English transcriptions, so if you're using another language, you should set this to
false
. For optimal configuration, you might also want to adjust the
waitSeconds
parameter (0.8 seconds is recommended by some users for better processing time). Let me know if you need any further assistance with this configuration! ๐Ÿ˜Š Sources: - [Discord Channel](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1329414710583627796) - [Discord Channel](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1343636482874933340) - [Customization Documentation](https://docs.vapi.ai/customization/speech-configuration)
k
Hi! Is your org on the weekly release channel?
a
Yes.
k
Ah - yeah, this functionality hasn't been released to the weekly backend yet. That will happen on Thursday
a
thanks!
v
Message marked as helpful by @yonnigm! ๐ŸŽ‰
n
Hi! How were you able to select LiveKit as an option? There is no such option in my assistant settings ๐Ÿ˜ฆ
a
Might have been the state of my dashboard maybe they removed it until they push to prod.
n
I see it now, but it doesnโ€™t work. Does it work for you?
a
not yet i think we have to wait until the push to prod