Where do I go to make this change?
From your Dashboard, locate the assistant that you wish to edit (most people only have one, but we support multiple assistants) and click the Control Panel (this is the button with the three dots, sometimes called an ellipsis menu). From there click Update Technical Config.
What does this page do?
This page allows you to tweak some of the technical configurations that define how the assistant works.
⚠️ It is important to run test calls after making any change to these values to make sure you are happy that the assistant acts and sounds the way you want.
1. Eagerness to respond
Controls how eager the agent is to respond.
Patient = less eager (waits longer)
Normal = default eagerness
Eager = more eager (responds sooner)
2. Max. Call Duration
The maximum number of seconds that a conversation can last. This is a hard cut-off that ends the call and is a way for you to control costs. It cannot be set to be less than 60 seconds. This is a limit that applies to both phone calls and webchats (if you have a chatbot embedded on your website).
3. Agent Turn Timeout
The maximum number of seconds since the user last spoke. If exceeded, the agent will respond and force a response.
4. Agent Silence Cut-off Time
The maximum number of seconds since the user last spoke. If exceeded, the call will terminate. Minimum 10 seconds.
5. Temperature
Temperature controls the randomness of the output. A higher temperature will result in more diverse and creative transcriptions, which can be useful for more nuanced or less clear audio. A lower temperature will make the transcription more deterministic and focused on the most probable words, which is great for clear audio where you want high accuracy.
6. Similarity Boost
Higher values will boost the overall clarity and consistency of the voice. Very high values may lead to sound distortions. Adjusting this value to find the right balance is recommended.
7. Speed
Most natural conversations occur at 0.9-1.1x speed. Depending on the voice, adjust slower for complex topics or faster for routine information.
8. Stability
Lower values (0.30-0.50) create more emotional, dynamic delivery but may occasionally sound unstable. Higher values (0.60-0.85) produce more consistent but potentially monotonous output.
9. LLM
This is the large language model that we use to power your conversational AI. You cannot change this value. We will update this if and when new models give greater capability for voice AI.