Skip to main content

Overview

Voice agents are the powerhouse of Outbox AI—perfect for outbound dialing, lead qualification, appointment booking, and more. They do have a steeper learning curve than chat agents, so use this guide as your reference while you build.
New to prompting? Check out our Prompting Guide for best practices on writing effective agent instructions.

Prompt Settings

The foundation of your voice agent starts with two key fields.
Core Prompt Settings

Prompt

Paste your full prompt here. This is the brain of your voice agent—it defines personality, objectives, and how to handle different scenarios. Important Considerations:
  • ⚠️ Words will be spoken aloud – Avoid complex symbols, unusual punctuation, or hard-to-pronounce terms
  • 🗣️ Write for speech – Use “twenty-five” instead of “25” for natural-sounding responses
  • 📝 Keep it conversational – The agent should sound human, not like it’s reading a script
Use the Generate button to let AI help you create or refine your prompt! See our Prompting Guide for detailed instructions.

First Message

Control how the agent opens the conversation. For Inbound Calls: Set a greeting so callers know who answered.
"Outbox AI, Jacob speaking—how can I help?"
"Thanks for calling Elite Fitness! This is Sarah. What can I do for you today?"
For Outbound Calls: Create a personalized opening that gets attention.
"Hi {{first_name}}, this is Sarah from Elite Fitness. I'm calling about your inquiry. Do you have a quick minute?"
Leave Blank: If you want the agent to wait for the caller to speak first (common for inbound support lines).

Tools

Give your voice agent superpowers by connecting it to external services and automations.
Call external services via Zapier, Make, or any webhook.Configuration:
  1. Enter your webhook URL
  2. Supply authentication headers if required
  3. Map variables from the conversation
  4. Define what data to return
Custom URL Tool
Use Cases:
  • Send lead data to your CRM
  • Check inventory or pricing in real-time
  • Trigger Zapier workflows
  • Update external databases
  • Verify customer information
Quick plug-ins for common tasks—no coding required.Available Tools:Cal.com Integration:
  • Get Free Slots – Fetch available appointment times
  • Book Appointment – Schedule meetings directly
  • Cancel/Reschedule – Modify existing bookings
GoHighLevel Integration:
  • Get Free Slots – Check calendar availability
  • Book Appointment – Schedule calls automatically
  • Find Or Create Contact – Manage contact records
  • Send SMS – Follow up via text after the call
Popular Tools:
  • Book AI Callback – Schedule the agent to call back later
  • Get Current Time – Reference accurate time/date info
  • Send SendGrid Email – Email confirmations or follow-ups
  • Send Twilio SMS – Text messages during or after calls
  • Solar Savings (US Only) – Calculate solar savings on the fly
Tool Library
The tool library is constantly expanding. Check back regularly for new integrations!
Choose a calendar and let the agent schedule appointments directly during the call.Currently Supported:
  • ✅ GoHighLevel calendars
  • ✅ Cal.com
Coming Soon:
  • 🔜 HubSpot
  • 🔜 Salesforce
Book Appointment
What the Agent Can Do:
  • Check real-time availability
  • Offer multiple time slots
  • Book the appointment on the call
  • Confirm details before finalizing
  • Send automatic confirmation messages
Transfer calls to live representatives with customizable destinations and transfer types.Configuration:
  1. Add multiple transfer destinations (phone numbers)
  2. Configure when to use each destination
  3. Set transfer type and messaging
  4. Customize what the agent says during transfer
Transfer Tool
Adding Transfer Destinations:
Transfer Tool Destinations
Transfer Destinations:Each destination can be customized with:
  • Description – When to use this transfer destination
  • Phone Number – E.164 format (e.g., +61412345678)
  • Transfer Message – What the agent says before transferring
  • Transfer Type – Choose from four options:
Transfer Types:
Simple transfer – Agent transfers the call immediately without any introduction.
  • ✅ Fastest transfer method
  • ✅ No additional setup required
  • ❌ Recipient has no context about the call
Intelligent transfer – Agent provides a summary of the conversation to the recipient.
  • ✅ Recipient knows what was discussed
  • ✅ Seamless handoff experience
  • ✅ Reduces repetition for the customer
Custom transfer – Agent delivers a specific message to the recipient before connecting.
  • ✅ Fully customizable introduction
  • ✅ Can include specific instructions
  • ✅ Perfect for specialized departments
Concierge transfer – Agent calls the destination first, shares context, and asks if they want the call.
  • ✅ Ensures the recipient is available before connecting
  • ✅ Lets the agent recap the conversation in real time
  • ✅ Protects callers from being routed to unprepared recipients; agent ends the call gracefully if declined
Example Setup:
Destination 1: Sales Team
- Description: "When caller is ready to purchase or has pricing questions"
- Message: "Let me connect you with our sales team who can help with pricing and next steps."
- Transfer Type: Warm Transfer with Summary

Destination 2: Technical Support
- Description: "When caller has technical issues or needs troubleshooting"
- Message: "I'll transfer you to our technical support team who specializes in these issues."
- Transfer Type: Warm Transfer with Message: "Customer needs help with [specific issue]"

Destination 3: On-Call Manager
- Description: "Escalations that need manager approval"
- Message: "I have a caller with an urgent escalation. Are you free to take it?"
- Transfer Type: Warm Transfer with Agent
Use Cases:
  • Route qualified leads to sales team
  • Transfer technical questions to support
  • Escalate complaints to management
  • Connect VIP customers to dedicated reps
  • Route by department or expertise
Pro Tip: Use conditional logic in your prompt to determine which destination to use based on the caller’s needs or responses.
Connect to Model Context Protocol (MCP) servers for advanced integrations with thousands of apps and services.Two Setup Options:When you choose the MCP Server tool type, you’ll be prompted with two options:Option 1: Custom MCP Server
Connect to your own custom MCP server (like Zapier MCP). Perfect for advanced users who want full control over their integrations.
Option 2: Preset MCP Applications
Choose from our curated list of preset MCP application servers. Quick setup with popular applications like Gmail, Google Sheets, Slack, and more.
Using Preset MCP Applications:
1

1. Select an Application

Choose an application from the preset MCP Application list (e.g., Gmail, Google Sheets, Slack, HubSpot, Salesforce, Airtable).
2

2. Authenticate Your Account

Connect and authenticate your account with the selected application. Outbox AI will guide you through the OAuth flow.
3

3. Choose Specific Tools

Select which specific tools from the application you want your agent to have access to. You have granular control over permissions.Example: For Gmail, you can give your agent access to:
  • ✅ Create draft emails
  • ❌ Send emails
  • ❌ Read emails
This allows you to control exactly what actions your agent can perform during calls.
4

4. Agent Can Use Tools

Once configured, your agent can perform the selected tasks through the MCP server during live calls.
Using Custom MCP Server (Zapier):
1

1. Visit Zapier MCP

Go to mcp.zapier.com and sign in with your Zapier account.
2

2. Create New MCP Server

Click “Create New MCP Server” and select “Other” as the MCP Client type.
Create MCP Server
3

3. Add Tools from 8,000+ Apps

Browse and select tools from Zapier’s extensive app library. Popular options include:
  • Google Sheets – Search, create, and update spreadsheets
  • Gmail – Send emails and manage inbox
  • Slack – Send messages and create channels
  • HubSpot – Manage contacts and deals
  • Salesforce – Update records and create tasks
  • Airtable – Query and update databases
4

4. Connect Your Apps

Authenticate with the apps you want to use. Zapier will guide you through OAuth flows for each service.
Select MCP Tools
5

5. Get Server URL

Once configured, click “Connect” and copy the MCP server URL.
Copy MCP Server URL
6

6. Add to Outbox AI

Select “Custom MCP Server” and paste the server URL into the MCP Server field in your voice agent settings.
MCP Server in Outbox
7

7. Select Specific Tools

Choose which tools from your MCP server to make available to your voice agent.
Select Tools for Agent
Example Use Cases:
Search customer data during calls:
  • Look up customer information from spreadsheets
  • Update appointment bookings in real-time
  • Track call outcomes and lead quality
Update customer records:
  • Create new contacts during calls
  • Update deal stages based on conversation
  • Add call notes and follow-up tasks
Send follow-up messages:
  • Email appointment confirmations
  • Send Slack notifications to team
  • Create tasks in project management tools
Advanced Features:
  • Real-time Data Access – Query live data during calls
  • Multi-app Workflows – Chain actions across different services
  • Custom Authentication – Secure access to your business tools
  • Error Handling – Graceful fallbacks when tools fail
Pro Tip: Start with 2-3 essential tools and gradually add more as you become comfortable with MCP integration. Too many tools can slow down response times.
MCP servers provide a standardized way for AI agents to interact with external tools and data sources during live calls. With preset MCP applications, you can quickly connect popular services with granular tool selection. For advanced integrations, custom MCP servers like Zapier give you access to 8,000+ apps without custom development.

Voice & Model Options

Configure your agent’s language, voice, intelligence, and background sound.

Language Selection

Choose the language and regional accent for your agent. Available Languages:
  • English (US) – American English accent
  • Spanish – Spanish language
  • French – French language
  • Bulgarian – Bulgarian language
  • Catalan – Catalan language
  • Czech – Czech language
  • Danish – Danish language
  • German – German language
  • Greek – Greek language
  • Estonian – Estonian language
  • Finnish – Finnish language
  • Hindi – Hindi language
  • Hungarian – Hungarian language
  • Indonesian – Indonesian language
  • Italian – Italian language
  • Japanese – Japanese language
  • Korean – Korean language
  • Lithuanian – Lithuanian language
  • Latvian – Latvian language
  • Malay – Malay language
  • Multilingual – Multiple languages support
  • Dutch – Dutch language
  • Norwegian – Norwegian language
  • Polish – Polish language
  • Portuguese – Portuguese language
  • Romanian – Romanian language
  • Russian – Russian language
  • Slovak – Slovak language
  • Swedish – Swedish language
  • Tamil – Tamil language
  • Tamazight – Tamazight language
  • Thai – Thai language
  • Turkish – Turkish language
  • Ukrainian – Ukrainian language
  • Vietnamese – Vietnamese language
  • Chinese – Chinese language
  • Chinese (China) – Chinese (China) language
  • Chinese (Simplified) – Chinese (Simplified) language
  • Chinese (Traditional) – Chinese (Traditional) language
  • Chinese (Taiwan) – Chinese (Taiwan) language
Language selection affects both the agent’s speech and its understanding of regional expressions and terminology.

Voice Selection

Choose from 1,000+ ElevenLabs voices to match your brand and audience perfectly.
Voice Provider Selection
Voice Library:
Browse All Available Voices: Visit app.getoutbox.ai/voice-library to listen to samples and preview the complete voice collection before making your selection.
Outbox AI offers access to ElevenLabs’ massive voice library with over 1,000 professionally trained voices covering:
  • Multiple accents – US, UK, Australian, Indian, and more
  • Diverse genders – Male, female, and neutral voices
  • Age ranges – Young, middle-aged, and mature voices
  • Tones – Professional, casual, energetic, empathetic, and more
Choosing the Right Voice:

Professional Services

Clear, articulate voices with neutral accents - Legal, accounting, medical - B2B sales - Corporate reception

Consumer Services

Warm, friendly voices with local accents - Fitness, hospitality - Retail, e-commerce - Local services

Sales & Marketing

Energetic, engaging voices - Outbound sales - Event bookings - Limited-time offers

Support & Care

Patient, empathetic voices - Customer support - Healthcare - Technical assistance
Pro Tip: Test multiple voices with the same prompt. The right voice can dramatically improve engagement and conversion rates.

Model Selection

Choose the AI model that powers your agent’s intelligence. Each model balances speed and reasoning ability differently.
All models are priced the same, so choose based on your needs for speed vs. intelligence, not cost!
700ms • Moderate • FastFaster than GPT-4.1 but with slightly reduced intelligence.
  • 🏃 Quick response times
  • 💬 Good for straightforward conversations
  • ⚠️ May struggle with complex scenarios
Best for: Simple appointment confirmations, basic FAQs, predictable conversation flows
510ms • Less Accurate • FastestThe fastest model, but with reduced reasoning ability.
  • ⚡⚡ Extremely fast (under 1 second)
  • 📝 Best for scripted interactions
  • ⚠️ Limited ability to handle unexpected questions
Best for: Appointment reminders, simple confirmations, highly scripted calls where speed matters most
600ms • Most Accurate • SlowerThe most intelligent GPT-4 model with superior reasoning.
  • 🎯 Exceptional accuracy and comprehension
  • 📚 Handles complex scenarios excellently
  • 💡 Better at handling objections and edge cases
  • ⏱️ Slightly slower than GPT-4.1
Best for: Complex sales conversations, technical support, consultative selling, handling difficult customers
1550ms • Smartest • SlowerThe most intelligent model available, but with noticeable latency.
  • 🎓 Exceptional reasoning capabilities
  • 🔍 Best for highly complex conversations
  • ⏱️ Significant delay (1.5+ seconds) may feel laggy
Best for: High-value consultations where accuracy matters more than speed, complex technical discussions, situations requiring deep reasoning
1450ms • Smart • ModerateSmart reasoning with slightly better speed than GPT-5.
  • 🧠 Advanced intelligence
  • ⏱️ Still slower than GPT-4 models
  • 🎯 Good for complex scenarios that don’t need full GPT-5 power
Best for: Complex conversations where you need strong reasoning but can’t afford GPT-5’s latency
1350ms • Smart • Fastest (of GPT-5 series)The fastest GPT-5 model with good intelligence.
  • 📊 Handles longer conversation histories
  • ⚡ Faster than other GPT-5 models
  • 🧠 Still intelligent, just not as advanced
Best for: Long conversations requiring extensive context, complex calls that need GPT-5 intelligence with better speed
Choosing the Right Model: Start with GPT-4.1 for most use cases. Only upgrade to GPT-4o or GPT-5 if you encounter specific scenarios requiring higher intelligence. Downgrade to Mini/Nano only if speed is critical and conversations are simple.

Model Configuration

Fine-tune your selected model’s behavior with advanced configuration options. Temperature
Control the randomness and creativity of your agent’s responses. Lower values make responses more focused and deterministic, while higher values allow for more varied responses.
Max Tokens
Set the maximum length of responses generated by the model. Adjust this based on your use case—shorter for quick confirmations, longer for detailed explanations.
Advanced Settings: Temperature and Max Tokens can be configured in your agent’s advanced settings. These settings allow you to fine-tune how your model responds to match your specific use case.

Voice Settings

Customize your selected voice with ElevenLabs’ advanced voice parameters for precise control over speech generation. Model Choose the ElevenLabs voice model that best fits your needs:
  • Eleven Turbo v2 – Fast, high-quality voice synthesis
  • Eleven Turbo v2.5 – Enhanced version with improved speed and quality
  • Eleven Multilingual v1 – Supports multiple languages
  • Eleven Multilingual v2 – Updated multilingual model with enhanced language support
  • Eleven English v1 – Optimized for English language synthesis
Stability
Default: 0.45
Increasing variability can make speech more expressive with output varying between re-generations. It can also lead to instabilities. Clarity + Similarity
Default: 0.65
Low values are recommended if background artifacts are present in generated speech. Speed
Default: 1.00
Controls the speed of speech generation. Style Exaggeration
Default: 0.00
High values are recommended if the style of the speech should be exaggerated compared to the uploaded audio. Higher values can lead to more instability. Setting this to 0.0 will greatly increase generation speed. Optimize Streaming Latency
Default: 1
Controls streaming latency optimization level (0-4). Use Speaker Boost
Boost the similarity of the synthesized speech and the voice at the cost of some generation speed.
Auto Mode
Reduces latency for complete sentences but may affect quality with partial phrases.
Fine-tuning Tips: Start with default values and adjust one parameter at a time to see how it affects your voice output. Small adjustments can make significant differences in how natural and expressive your agent sounds.

Background Sound

Add ambient background noise to make your calls feel more human and authentic. Available Options:
  • Office – General office sounds (keyboard typing, subtle background chatter)
  • Lounge – General lounge sounds (subtle café/waiting room ambience)
  • Custom Upload – Bring your own ambience by uploading an MP3 file (loops automatically once processed)
  • Mute – No background sound (clean audio only)
When to Use Background Sound:
Background sounds make outbound calls feel more authentic and less “robotic.” The subtle ambience suggests the caller is in a real office environment.
Light office sounds help the call feel like it’s coming from a real receptionist.
Support calls should be crystal-clear. Background noise can make it harder to hear, especially if the customer is in a noisy environment.
If your audio levels are inconsistent or too quiet, background sounds can make it worse. Fix audio issues first, then add ambience.
Test with and without background sound to see what feels right for your use case. What works for one industry might not work for another.
Looking for something unique? Upload an MP3 loop through the background sound picker to create a custom atmosphere for your callers.

Knowledge Base

Give your agent access to company information, product details, policies, and more. Choose from three methods:
Performance Impact: Knowledge base lookups add 2-4 seconds of latency per query during calls. Best reserved for inbound reception, help-desk scenarios, or when accuracy matters more than speed. For fast-paced outbound calls, put FAQs directly in your prompt instead.
Drop files directly into the knowledge base—the agent will read and understand them.Supported Formats:
  • 📄 PDFs
  • 📝 Word documents (.docx, .doc)
  • 📊 CSV files
  • 📋 Plain-text files (.txt)
  • 🔤 Markdown files (.md)
File Upload
Best for:
  • Product manuals
  • Company policies
  • FAQs
  • Pricing sheets
  • Training materials
Paste any URL and Outbox AI will scrape the entire site into clean, AI-readable Markdown.Powered by Firescraper – Advanced scraping technology that handles:
  • JavaScript-rendered content
  • Multi-page sites
  • Dynamic content
  • Complex site structures
Website Scrape
Best for:
  • Company websites
  • Product documentation
  • Help centers
  • Blog content
  • Knowledge base articles
The scraper will follow links and capture the entire site structure, not just a single page!
Paste raw text directly into the knowledge base.
Plain Text
Best for:
  • Custom instructions
  • Quick reference information
  • Company values and mission
  • Temporary information
  • Testing and prototyping
You can combine all three methods! Add files, scrape websites, and paste text for maximum coverage.

Advanced Settings

Fine-tune your agent’s behavior with these powerful configuration options.

Time Zone

Essential for accurate appointment booking. Set the agent’s time zone so it can correctly interpret phrases like “tomorrow at 3pm” or “next Monday morning.”
Critical for booking tools: Without the correct time zone, appointments may be scheduled for the wrong time, causing missed meetings and frustrated customers.

HIPAA Compliance

Stop call logs and recordings from being stored. When HIPAA Compliance is enabled:
  • ❌ No call recordings are stored
  • ❌ No transcriptions are saved
  • ❌ No logs are kept
  • ✅ Only basic call metadata (duration, status) is retained
When to Enable:
  • Healthcare providers
  • Legal firms
  • Financial services
  • Any regulated industry requiring data protection
Trade-off: With HIPAA mode enabled, you won’t be able to review call recordings for training or quality assurance purposes.

Forwarding Number

Automatically pass a qualified caller to a live rep. Enter a phone number in E.164 format (e.g., +61412345678) to transfer calls. How It Works:
  1. Agent qualifies the lead during the call
  2. Agent says: “Great! Let me connect you with one of our specialists.”
  3. Call is transferred to the forwarding number
  4. Live rep picks up and continues the conversation
Use Cases:
  • Hot leads ready to buy
  • Technical questions beyond the agent’s scope
  • VIP customers requesting personal service
  • Emergency or urgent situations
Pro Tip: Use conditional logic in your prompt to decide when to forward. For example: “If the caller wants to speak to someone immediately, forward the call. Otherwise, book an appointment.”

Key Terms

Improve transcription accuracy for unusual names, brands, suburbs, etc. Add terms that the speech-to-text engine might misunderstand. Separate each term with a space. Examples:
Outbox Mandurah Fremantle Joondalup CrossFit Pilates HIIT
Burleigh Currumbin Coolangatta Broadbeach Robina
What to Add:
  • Business names (especially unique spellings)
  • Suburb and location names
  • Product names and brands
  • Industry-specific terminology
  • Uncommon proper nouns
Key terms help the transcription engine recognize these words correctly during the call, leading to better comprehension and fewer errors.

Voicemail Message

What to say if the system detects voicemail after ~20 seconds. Example:
"Hi {{first_name}}, this is Sarah from Elite Fitness. I was just calling to follow up on your inquiry about our membership. Give us a call back at 08 1234 5678, or I'll try you again later. Have a great day!"
Best Practices:
  • ✅ Keep it under 15 seconds
  • ✅ Include your callback number
  • ✅ Give a reason for the call
  • ✅ Sound natural and friendly
  • ❌ Don’t oversell or sound desperate
Leave it blank if you don’t want the agent to leave voicemails. The call will simply end and be logged as “no answer.”

End Call Message

Last line before hanging up. Examples:
"Thanks for your time today! You'll receive a confirmation email shortly. Have a great day!"
"Perfect! We'll see you on Tuesday at 3pm. Looking forward to it!"
"No worries at all. Feel free to call us back if you change your mind. Take care!"
Leave Blank: If you want the agent to disconnect silently after completing its objective.

Unqualified Prompt

Define disqualifying criteria so calls are automatically tagged “Unqualified.” Example:
Mark the call as unqualified if any of the following are true:
- The caller is a renter (we only work with homeowners)
- The caller is over 75 years old
- The caller is not the decision-maker
- The property is commercial (we only do residential)
Why Use This: Unqualified tags integrate with GoHighLevel automations, allowing you to:
  • Automatically remove unqualified leads from sequences
  • Trigger different follow-up workflows
  • Tag contacts for future remarketing
  • Keep your pipeline clean and focused
Be specific! Vague criteria lead to inconsistent tagging. Clear rules ensure reliable automation.

Summary Prompt

Tell Outbox AI how to format the call summary posted back to your CRM.
Summary Prompt
Example:
Summarize this call in 2-3 sentences. Include:
- The caller's main question or goal
- Whether an appointment was booked (and when)
- Any objections or concerns mentioned
- Next steps

Format it in plain English, suitable for a sales rep to read quickly.
Default Behavior: If left blank, Outbox AI generates a standard summary automatically. Customization Ideas:
  • Bullet points for easy scanning
  • Include specific fields for your CRM
  • Highlight key selling points mentioned
  • Note urgency level or buying intent

Scoring Prompt

Define how the call should be scored from 0-100. Example:
Rate how successful this call was from 0-100. 0 means a true failure: caller was upset/angry, tools malfunctioned, or a serious error occurred.
100 means a perfect outcome: caller was engaged, happy, and all tools worked correctly.
50 means a neutral/middle call where some interaction happened but nothing notable was achieved.
If the call was very short (1-5 seconds), unanswered, or had no meaningful interaction, do NOT score it as 0. Instead, treat it as a neutral/no-outcome call (e.g., 30-40).
Consider caller engagement, tool success, and overall outcome when assigning the score.
How to Use Scores:
  • Route high-scoring leads to sales immediately
  • Add low-scoring leads to nurture campaigns
  • Track conversion rates by score range
  • Optimize agent performance over time
Scores are returned with the call completion webhook and visible in GoHighLevel custom fields.

Webhook URL

Where to send the end-of-call report. Enter a URL to receive a POST request with detailed call information immediately after each call completes. Request Format: The webhook sends a POST request with the following JSON payload:
{
  "id": "thread-uuid",
  "status": "did-succeed",
  "summary": "Caller wanted to book an appointment for teeth cleaning. Successfully scheduled for Tuesday at 3pm. Caller was friendly and confirmed contact details.",
  "agent": {
    "id": "agent-uuid",
    "name": "Dental Receptionist",
    "phone_number": "+61412345678"
  },
  "direction": "outbound",
  "duration": 142,
  "user": {
    "name": "John Smith",
    "phone_number": "+61498765432",
    "external_id": "ghl-contact-123"
  },
  "transcript": "Full conversation transcript here..."
}
Fields Explained:
  • id – Unique thread identifier
  • status – Call outcome (did-succeed, did-not-answer, error, etc.)
  • summary – AI-generated summary of the call
  • agent.id – The agent’s unique ID
  • agent.name – The agent’s name
  • agent.phone_number – The number the agent called from
  • direction – “inbound” or “outbound”
  • duration – Call length in seconds
  • user.name – Contact’s full name
  • user.phone_number – Contact’s phone number
  • user.external_id – Contact’s ID in your CRM (e.g., GoHighLevel contact ID)
  • transcript – Complete conversation transcript
Use Cases:
  • Send data to Zapier or Make
  • Update your CRM with call results
  • Trigger follow-up automations based on status
  • Log analytics in custom dashboards
  • Route hot leads to sales teams
  • Create tasks for follow-ups
Test your webhook with a tool like webhook.site to see exactly what data is being sent before connecting your production systems.

What to tell the user if you’re recording the call. Example:
"Just so you know, this call may be recorded for quality and training purposes."
Legal Requirement: Many jurisdictions require consent before recording calls. Check your local regulations and always inform callers if recording is enabled.

Log to CRM

Log the recording and transcript of these calls into your CRM. When enabled:
  • ✅ Full transcript is added to the contact record in GoHighLevel
  • ✅ Audio recording link is attached
  • ✅ Call summary appears in the timeline
  • ✅ Score and status are logged
Disable When:
  • HIPAA compliance is required
  • Calls are purely transactional (confirmations, reminders)
  • You’re doing high-volume testing

Testing & Deployment

Test your agent thoroughly before sending it live to customers.

Test Your Agent

Test your voice agent before going live using either web-based calling or real phone calls.

Option 1: Test via Web Call

Click the Test button to talk to your agent directly from your browser—no phone required. What This Does:
  • Opens a web-based call interface in your browser
  • No phone number required
  • Instant feedback on prompt behavior
  • Perfect for rapid iteration and quick tests
Best For:
  • Quick prompt testing and adjustments
  • Checking tool integrations
  • Verifying voice and tone
  • Debugging conversation flows
  • Fast iteration during development
Test with real scenarios that customers will encounter, not just happy-path conversations. Try to break it!

Option 2: Test via Phone Call

Send a real phone call to yourself to test the complete customer experience.
Test Phone Call
1

Select Your Agent

Choose which voice agent to test
2

Enter Your Phone Number

Use your mobile or desk phone (E.164 format: +61412345678)
3

Click Send Test Call

The agent will call you within seconds
4

Have a Conversation

Test booking flows, objections, edge cases, etc.
5

Review the Call

Check the transcript, summary, and score in Conversations
Why Test on a Real Phone:
  • ✅ Experience exactly what customers hear
  • ✅ Test call quality and audio levels
  • ✅ Check latency and response times in real-world conditions
  • ✅ Verify transcription accuracy
  • ✅ Ensure tools work end-to-end
  • ✅ Test caller ID display
  • ✅ Validate voicemail detection
Test calls are billed at standard rates, but they’re worth every cent to catch issues before going live!

Assign a DID (phone number) to an agent so incoming calls trigger the right workflow.
Link Numbers
Navigate to Phone Numbers settings to:
  1. Add new phone numbers
  2. Assign numbers to specific agents
Use Cases:
  • Dedicated support line for customer service agent
  • Separate numbers for different campaigns

Share Button

Demo your agents with sharable web and phone call pages. Click the Share button to get:

Web Call Page

A browser-based demo where anyone can talk to your agent without a phone.
Share Button
Perfect For:
  • Internal demos to your team
  • Client presentations
  • Training new staff
  • Quick testing without using phone credits

Phone Call Page

A landing page with a “Call Now” button that triggers the agent to call the visitor.
Share Button
Perfect For:
  • Website “Call Me Back” buttons
  • Sales demos for prospects
  • Trade show displays
  • Email campaigns (“Click to speak with us”)
Pro Tip: Use the phone call page to let prospects try your service risk-free. It’s a powerful demo tool!

Monitor Results

Track performance and identify issues across three key views.

Conversations

Only connected calls – View text, audio, duration, and cost.
Conversations View
What You’ll See:
  • 📝 Full transcript of the conversation
  • 🎧 Audio recording playback
  • ⏱️ Call duration and timestamps
  • 💰 Cost per call
  • 📊 Call score (0-100)
  • ✅ Status (completed, unqualified, forwarded, etc.)
  • 🏷️ Summary and notes
Use This View To:
  • Review successful calls for training
  • Identify what’s working well
  • Spot patterns in customer questions
  • Improve your prompt based on real conversations

Call Logs

Every attempt, including voicemail and errors.
Call Logs
What You’ll See:
  • All outbound call attempts
  • Inbound calls (answered and missed)
  • Voicemails detected
  • Failed calls (wrong number, carrier issues, etc.)
  • No-answer scenarios
Status Types:
  • Completed – Call connected and finished successfully
  • 📞 Forwarded – Call transferred to a human
  • 📧 Voicemail – Agent left a message
  • Error – Technical failure
  • ⏭️ No Answer – Contact didn’t pick up
  • 🚫 Unqualified – Prospect didn’t meet criteria
Use This View To:
  • Track call success rates
  • Identify problematic phone numbers
  • Monitor voicemail detection accuracy
  • Spot systematic errors or issues

Call Queue

Overflow when concurrency is maxed, scheduled callbacks, or when wallet credit is low.
Call Queue
Calls Enter the Queue When:
  • ⏳ All concurrent call slots are full
  • 📅 Call is scheduled for a future time (callbacks)
  • 💳 Wallet balance is too low to place the call
  • 🔄 Retry attempts are pending
Queue Management:
  • ▶️ Resume – Process queued calls immediately
  • ⏸️ Pause – Hold calls in queue without processing
  • Cancel – Remove calls from queue entirely
Monitoring:
  • See how many calls are waiting
  • Identify why calls are queued
  • Prioritize urgent callbacks
  • Top up credits if needed
High Queue = Problem: If your queue is consistently full, you need to either: - Increase your concurrent call limit - Add more wallet credits - Slow down your outbound campaigns

Best Practices

Don’t overthink model selection. GPT-4.1 handles 95% of use cases perfectly. Only upgrade if you encounter specific limitations.
Before writing a complex prompt, test the voice itself:
  1. Create a simple “Hello, this is a test” agent
  2. Call yourself
  3. Evaluate clarity, tone, and professionalism
  4. Try 2-3 different voices
  5. Pick the winner, then build your prompt
The first 3 seconds determine whether someone hangs up or engages:✅ Good: “Hi Sarah, this is Jake from Elite Fitness. Quick question about your inquiry—got a minute?”❌ Bad: “Hello! Thank you so much for your interest in Elite Fitness. My name is Jake and I’m calling today to follow up on the form you submitted on our website about our premium membership packages…”Get to the point fast.
If you’re getting transcription errors (wrong suburb names, mangled product names), don’t hesitate to add 20-30 key terms. It makes a huge difference.
If your agent feels “laggy”:
  • Remove knowledge base (adds 2-4s per query)
  • Downgrade model (GPT-5 → GPT-4.1)
  • Simplify tool complexity
  • Shorten your prompt
Speed matters in voice. Aim for under 1.5 second response times.
Listen to 5-10 calls every week:
  • What objections keep coming up?
  • Where does the agent get confused?
  • What questions can’t it answer?
  • Where do people hang up?
Update your prompt based on real patterns, not assumptions.

Troubleshooting

Problem: The voice feels unnatural or scripted.Solutions:
  • Enable Background Sound (Office or Lounge)
  • Add filler words to your prompt (“um,” “ah,” “let me check”)
  • Use contractions (“I’m” not “I am,” “we’re” not “we are”)
  • Test a different voice with more personality
  • Avoid overly formal language in your prompt
Problem: Audio is choppy, quiet, or unclear.Solutions:
  • Test a different voice provider
  • Disable background sound if volume is low
  • Check that the caller’s connection is stable
  • Verify you’re not exceeding concurrent call limits
  • Contact support if issue persists across multiple calls
Problem: Long pauses between responses (over 3 seconds).Solutions:
  • Disable knowledge base if enabled
  • Switch to a faster model (GPT-5 → GPT-4.1)
  • Simplify tool logic and reduce API calls
  • Shorten your prompt (aim for under 2,000 words)
  • Remove complex conditional logic
Problem: The agent isn’t using the tools you’ve configured.Solutions:
  • Make tool usage explicit in your prompt: “When the caller wants to book, use the book_appointment tool”
  • Test the tool manually to ensure it’s working
  • Check API keys and authentication
  • Review tool logs for error messages
  • Simplify the tool trigger conditions
Problem: Names, locations, or terms are misheard.Solutions:
  • Add problematic words to Key Terms
  • Use phonetic spelling if needed (e.g., “Mandjoogoordap” for “Mandogalup”)
  • Test in a quiet environment first
  • Ensure the caller speaks clearly
  • Switch to a model with better transcription (GPT-4o or GPT-5)
Problem: Calls aren’t being placed immediately.Solutions:
  • Check your wallet balance – top up if low
  • Verify you haven’t hit your concurrent call limit
  • Review scheduled callback times
  • Resume the queue if it’s paused
  • Contact support to increase limits if needed

Next Steps