Skip to main content
The Voice Configuration page (Channels > Voice > Voice configuration) controls voice-specific settings including model selection, greeting, and disclaimer behavior.
Greeting and disclaimer settings are in Voice Configuration, separate from shared agent configuration in Build > Agent.

​
Model selection

Select the language model that powers your voice agent.
​
Large language model
dropdown
Choose the LLM for voice conversations. PolyAI’s Raven models are recommended for voice — they are purpose-built for conversational AI and deliver the most natural, grounded responses.
Recommended for voice: PolyAI’s Raven 3.5 is purpose-built for conversational voice AI. It produces concise, natural responses without needing example utterances in your prompts — just add raw information and Raven converts it into conversational speech. Raven 3.5 supports 24+ languages, delivers sub-300ms latency, and includes auto-reasoning, out-of-domain detection, and built-in safety.
For a full list of available models, see the Model page.

​
Voice greeting

Configure what your agent says when a call begins.
​
Greeting message
string
The first thing your agent says when answering a call.Example: “Thank you for calling. How can I help you today?”
Keep your greeting concise. Long greetings can frustrate callers who want to get to the point quickly.

​
Voice disclaimer

Configure a disclaimer message that plays at the start of calls.
​
Disclaimer message
string
A message informing callers about call recording or other legal requirements.Example: “This call may be recorded for quality and training purposes.”
​
Disclaimer voice
string
You can use a separate voice for the disclaimer to distinguish it from the main agent voice. Configure this in Agent Voice.

​
Call handling settings

Additional settings that affect how calls are handled:
  • Silence timeout - How long to wait during silence before prompting the caller
  • Max call duration - Maximum length of a call before automatic termination
  • End of call behavior - What happens when a call ends (e.g., trigger CSAT survey)

​
Environment behavior

Voice configuration follows the same branching behavior as other channel settings:
  • Make changes in Sandbox for testing
  • Promote to Pre-release for UAT
  • Deploy to Live for production
Last modified on March 31, 2026