Voice configuration

Configure model selection, greeting, disclaimer, safety filters, and call handling settings.

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 designed for conversational AI and deliver the most natural, grounded responses.

Recommended for voice: PolyAI’s Raven 3.5 is designed for conversational 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.

Safety filters

Safety filters are configured on a per-channel basis. The voice channel has its own safety filter settings, separate from the chat channel and the project-wide defaults.

Enable safety filters · boolean

When enabled, applies content filtering to voice responses. These filters apply to the voice channel only. Default settings can be managed on the Configure > General page.

When safety filters are enabled, adjust the strictness for each category using the sliders:

Category	Description
Violence	Controls filtering of violent content (Lenient → Strict)
Hate	Controls filtering of hateful or discriminatory content (Lenient → Strict)
Sexual content	Controls filtering of sexually explicit content (Lenient → Strict)
Self-harm	Controls filtering of self-harm related content (Lenient → Strict)

The jailbreak attack filter is always enabled and cannot be turned off.

More lenient settings allow a wider range of content through. Review your use case and compliance requirements when adjusting these settings.

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

Related pages

Agent Voice

Configure voice selection and settings

Audio management

Optimize latency and manage cached audio

Response control

Control response timing and behavior

Chat configuration

Configure the webchat channel equivalent