Skip to main content

Advanced Settings

The Advanced Settings page provides access to technical and debugging configurations for your voice agent. Most agents work well with the default settings, but these options allow you to fine-tune behavior for specific use cases.

When to Use Advanced Settings

For most agents, the default settings are optimal. Only modify these settings if you have specific technical requirements or are experiencing issues that require fine-tuning.

Environment

Select the deployment environment for your agent:

  • Development: For testing and experimentation. Use this when building and testing new features.
  • Staging: For pre-production validation. Use this to test changes before deploying to production.
  • Production: For live customer interactions. Only use this for agents that are ready for real customer conversations.
note

The environment setting helps you organize agents and track which ones are in active use versus testing.

Turn Detection Eagerness

Controls how quickly the AI detects when the user has finished speaking.

Options:

  • High (most responsive): The agent responds quickly, which feels snappy but may occasionally interrupt if the customer pauses mid-sentence. This is the default.
  • Medium (balanced): A balanced approach that waits a bit longer before responding.
  • Low (most patient): The agent waits longer to ensure the customer is truly finished speaking. Use this if customers frequently get interrupted.

When to adjust:

  • If customers complain about being interrupted, lower the eagerness
  • If conversations feel slow or awkward due to long pauses, increase the eagerness
  • For customers who speak slowly or take pauses while thinking, use Low

Default: High

Initial Mute Duration

Duration in milliseconds to keep the caller muted at the start of the conversation.

This allows your agent to introduce itself without interruption, which is especially useful for:

  • Longer greeting messages
  • Agents that provide important upfront information
  • Scenarios where you want to ensure the introduction is heard completely

Example values:

  • 0 - No mute (customer can speak immediately)
  • 3000 - 3 seconds (recommended for standard greetings)
  • 5000 - 5 seconds (for longer introductions)

Default: 0 (disabled)

Keypress Collection (DTMF)

Enable your agent to collect keypresses from the caller's phone keypad. This is useful for:

  • Collecting account numbers or PINs
  • Multi-factor authentication
  • IVR-style menu navigation
  • Collecting numeric information that's easier to type than speak

Configuration

Enable keypress collection: Turn this on to activate DTMF collection.

When enabled, you can configure:

Maximum Digits

The maximum number of digits to collect.

  • Leave empty or set to 0 for no limit (digits are collected until timeout or # key is pressed)
  • Set a specific number (e.g., 4) to stop collection after that many digits

Example values:

  • 4 - For collecting a PIN
  • 10 - For collecting a phone number
  • 16 - For collecting a card number
  • 0 or empty - No limit (collect until timeout or #)

Range: 0-20 digits

Timeout (seconds)

Number of seconds to wait after the last keypress before timing out and returning the collected digits.

The timeout resets after each keypress is captured, so it represents the pause duration between keypresses, not the total collection time.

Example values:

  • 5 - Standard timeout (recommended)
  • 10 - Longer timeout for uncertain inputs

Range: 1-60 seconds

Default: 5 seconds

Deployment Settings

Genesys Language Parameter

When enabled, the conversation language will be set based on the Language parameter from Genesys AudioHook. This overrides the default transcription language and restricts the allowed languages to only the Genesys-provided language.

Use this when:

  • You're using Genesys Cloud as your phone system
  • You want language to be automatically detected based on Genesys routing
  • You have multilingual agents that need to adapt to different caller languages

Default: Disabled

Summary of Conversations

Customize how your agent generates summaries of conversations. Summaries are automatically created after each conversation and help you quickly understand what happened without reading full transcripts.

Language Instructions

Define which language(s) should be used for summaries and when.

Example:

Use either Dutch (preferred) or English (if the transcript is in English).

Tips:

  • Specify your preferred language first
  • Include fallback languages for multilingual scenarios
  • Keep it concise and clear

Summary Content Instructions

Define the structure and content of the summary. Specify what information should be included and in what format.

Example:

- one sentence describing the topic of the conversation with high specificity.
For example, "the customer called about a stolen card that they want to block"
- [if applicable] one sentence explaining if and how the customer was identified.
For example, "I identified the customer by their date of birth, address and name."
If you did not identify the customer, you can omit this sentence.
- one sentence describing the outcome of the conversation.
For example, "The customer was unable to block the card themselves because they
lost their phone with the card. I have blocked the card for them and requested
a new card to be sent to them."

Tips:

  • Be specific about what information to include
  • Provide example outputs for clarity
  • Structure it as a bulleted list for easier reading

Information to Exclude

List types of information that should never be included in summaries for privacy, security, and compliance reasons.

Example:

- any of the customer's personal information such as name, address, phone number, email, etc.
- any sensitive information such as account numbers, social security numbers, etc.
- any sensitive information such as religious topics, political topics, or health related information.
Even if the customer mentions it, you should not include it in the summary.
- try not to infer gender unless that is explicitly stated by the customer.
Instead, use "the customer" or "them" as appropriate.

Tips:

  • Be comprehensive about excluded information types
  • Consider privacy regulations (GDPR, HIPAA, etc.)
  • Include both obvious (PII) and subtle (gender assumptions) exclusions

Good Summary Examples

Provide examples of well-written summaries that follow your guidelines. These help the AI understand your expectations.

Example:

The customer called about a stolen card that they want to block. I identified
the customer by their date of birth, address and name. The customer was unable
to block the card themselves because they lost their phone with the card. I have
therefore blocked the card for them and requested a new card to be sent to them.

Tips:

  • Include 1-3 complete examples
  • Make examples realistic and specific to your use case
  • Show the desired tone and level of detail

Bad Summary Examples

Provide examples of poor summaries with explanations of what makes them inadequate. This helps the AI learn what to avoid.

Example:

The customer, Dave Mills, called about their card. I identified Dave according
to policy. It was stolen when he left his mosque. I blocked it and did the
usual follow up.

-> This is a bad summary because it includes the customer's name, the fact that
he left his mosque, it is not specific about the topic, it makes assumptions
about gender, and it did not specify that a new card was requested.

Tips:

  • Include the bad example and an explanation of why it's bad
  • Use the -> or similar marker to separate example from explanation
  • Cover different types of common mistakes

Danger Zone

Delete Agent

Deleting an agent archives the agent configuration and prevents it from being used for new phone calls.

What happens when you delete an agent:

  • The agent configuration is archived and can no longer be used
  • The agent will not appear in phone number assignments
  • Past conversations remain available in the conversation history
  • The deletion cannot be undone
Permanent Action

Agent deletion is permanent and cannot be undone. Make sure you really want to delete the agent before proceeding.

Before deleting:

  • Ensure no phone numbers are assigned to this agent
  • Export any configuration you might need for reference

Saving Changes

Always click Save at the bottom of the page after making changes. Changes take effect immediately for new conversations.