---
title: "Voice AI for Customer Support: How to Deploy Conversational Voice Bots That Delight Customers in 2026"
description: Discover how to deploy voice AI for customer support in 2026. Learn how conversational voice bots reduce costs, scale service, and delight customers 24/7.
image: https://media.giphy.com/media/v1.Y2lkPTc5MGI3NjExcGU2OWFlMjY4YWJkZjQxYTgzYzE5YmY4ZDI4MDVmZGE2MDc0NjYwZiZlcD12MV9pbnRlcm5hbF9naWZfYnlfaWQmY3Q9Zw/l46Cy1rHbQ92uuLXa/giphy.gif
---
[.png)](https://www.getdarwin.ai/en?utm_source=organic)
Industries
[ Automotive](https://www.getdarwin.ai/en/industrias/automotriz?utm_source=organic) [ Education](https://www.getdarwin.ai/en/industrias/educacion?utm_source=organic) [ Real State](https://www.getdarwin.ai/en/industrias/inmobiliario?utm_source=organic) [ Retail](https://www.getdarwin.ai/en/industrias/retail?utm_source=organic) [ Health](https://www.getdarwin.ai/en/industrias/salud?utm_source=organic) [ Insurance](https://www.getdarwin.ai/en/industrias/seguros?utm_source=organic) [ Services](https://www.getdarwin.ai/en/industrias/servicios?utm_source=organic)
IA Workforce
[ Alba, Inbound](https://www.getdarwin.ai/en/worker/alba?utm_source=organic) [ Bruno, Outbound](https://www.getdarwin.ai/en/worker/bruno?utm_source=organic) [ Eva, CX](https://www.getdarwin.ai/en/worker/eva?utm_source=organic) [ Sophia, Post-Sales](https://www.getdarwin.ai/en/worker/sophia?utm_source=organic) [ Lucas, Cobranzas](https://www.getdarwin.ai/en/worker/rio?utm_source=organic)
[About Us](https://www.getdarwin.ai/en/about-us?utm_source=organic) [Partners](https://www.getdarwin.ai/en/partners?utm_source=organic)
Resources
[ Blog](https://blog.getdarwin.ai/en/) [ Press](https://www.getdarwin.ai/en/press?utm_source=organic) [ ROI Calculator](https://www.getdarwin.ai/en/roi-calculator?utm_source=organic) [ Whatsapp Link Generator](https://www.getdarwin.ai/en/whatsapp-link-generator?utm_source=organic) [ Whatsapp QR Generator](https://c2w.getdarwin.ai/en)
EN
[ES](https://blog.getdarwin.ai/es/?hsLang=en) [EN](https://blog.getdarwin.ai/en/) [PT](https://blog.getdarwin.ai/pt-br/?hsLang=en)
[Login](https://app.getdarwin.ai/login) [Try Darwin ](https://app.getdarwin.ai/signup?landing=homepage&language=en&utm_source=organic_homepage&utm_medium=LeadGen)
Industries
[ Industries](https://www.getdarwin.ai/en/industrias/automotriz?utm_source=organic) [ Education](https://www.getdarwin.ai/en/industrias/educacion?utm_source=organic) [ Real State](https://www.getdarwin.ai/en/industrias/inmobiliario?utm_source=organic) [ Retail](https://www.getdarwin.ai/en/industrias/retail?utm_source=organic) [ Health](https://www.getdarwin.ai/en/industrias/salud?utm_source=organic) [ Insurance](https://www.getdarwin.ai/en/industrias/seguros?utm_source=organic) [ Services](https://www.getdarwin.ai/en/industrias/servicios?utm_source=organic)
IA Workforce
[ Alba, Inbound](https://www.getdarwin.ai/en/worker/alba?utm_source=organic) [ Bruno, Outbound](https://www.getdarwin.ai/en/worker/bruno?utm_source=organic) [ Eva, CX](https://www.getdarwin.ai/en/worker/eva?utm_source=organic) [ Sophia, Post-Sales](https://www.getdarwin.ai/en/worker/sophia?utm_source=organic) [ Lucas, Collections](https://www.getdarwin.ai/en/worker/rio?utm_source=organic)
[About Us](https://www.getdarwin.ai/en/about-us?utm_source=organic) [Partners](https://www.getdarwin.ai/en/partners?utm_source=organic)
Resources
[ Blog](https://blog.getdarwin.ai/en/) [ Press](https://www.getdarwin.ai/en/press?utm_source=organic) [ ROI Calculator](https://www.getdarwin.ai/en/roi-calculator?utm_source=organic) [ Whatsapp Link Generator](https://www.getdarwin.ai/en/whatsapp-link-generator?utm_source=organic) [ Whatsapp QR Generator](https://c2w.getdarwin.ai/en)
EN
[ES](https://blog.getdarwin.ai/es/?hsLang=en) [EN](https://blog.getdarwin.ai/en/) [PT](https://blog.getdarwin.ai/pt-br/?hsLang=en)
[Login](https://app.getdarwin.ai/login) [Try Darwin ](https://app.getdarwin.ai/signup?landing=homepage&language=en&utm_source=organic_homepage&utm_medium=LeadGen)
# Voice AI for Customer Support: How to Deploy Conversational Voice Bots That Delight Customers in 2026
15 de April, 2026
## The Rise of Voice AI: Why Conversational Voice Bots Are Reshaping Customer Support in 2026
When most people think of AI in customer service, they imagine text-based chatbots — those pop-up chat widgets that handle FAQs and pass complex issues to a human agent. But in 2026, a far more powerful channel has matured to the point of mainstream deployment: **voice AI**.
Voice AI for customer support uses natural language processing (NLP), speech recognition, and conversational AI to conduct real spoken conversations with customers — handling everything from billing inquiries and appointment scheduling to technical troubleshooting and order tracking. And unlike the frustrating IVR trees of the past ("Press 1 for billing, Press 2 for…"), modern voice AI actually *understands* what customers say, responds naturally, and resolves issues end-to-end without human intervention.
In this comprehensive guide, we'll explore how voice AI works, why it's become mission-critical for customer-facing businesses, and exactly how to deploy conversational voice bots that customers actually enjoy interacting with.
## What Makes Modern Voice AI Different from Old IVR Systems
Traditional Interactive Voice Response (IVR) systems have existed since the 1970s. They're the reason customers groan when they call a support line. Limited to menu trees and DTMF tones, legacy IVR forces customers into rigid scripts that rarely match their actual needs. Studies show that **67% of customers hang up in frustration** when they can't reach a human quickly through an IVR system.
Modern voice AI is fundamentally different in four key ways:
### 1. Natural Language Understanding (NLU)
Today's voice AI systems are powered by large language models and advanced NLU that can parse the intent behind what a customer says — not just pattern-match keywords. A customer saying "I need to change the delivery address for the order I placed yesterday" is understood in full context, not broken down into a rigid decision tree.
### 2. Dynamic, Context-Aware Conversations
Modern voice AI maintains context across the entire call. If a customer mentions their account number at the start, the bot remembers it throughout. It can ask clarifying questions, handle topic switches gracefully, and adapt its responses based on the customer's tone and history.
### 3. Real-Time CRM and Data Integration
Voice AI in 2026 connects directly to your CRM, order management system, ticketing platform, and knowledge base. This means the bot can pull a customer's order history, check inventory status, process a refund, or update contact details — all in real time, during the call.
### 4. Seamless Human Escalation
The best voice AI systems know their limits. When sentiment analysis detects frustration, or when a query exceeds the bot's confidence threshold, the system transfers the call to a human agent — along with a full transcript and context summary so the agent doesn't have to ask the customer to repeat themselves.
## The Business Case for Voice AI in Customer Support
The ROI of voice AI is compelling, especially for businesses with high inbound call volumes. Here are the key metrics that drive adoption:
### Cost Reduction
The average cost of a human-handled support call in North America is **$8-15 per interaction**, depending on complexity and industry. A voice AI interaction costs as little as **$0.10-0.50**. For a business handling 10,000 calls per month, shifting 60% to AI resolution delivers **$50,000-$80,000 in monthly savings**.
### 24/7 Availability Without Overtime
Voice AI doesn't sleep, take vacations, or call in sick. Businesses that deploy voice bots see a sharp reduction in after-hours calls that previously went unanswered — or required expensive overnight staffing. This is particularly valuable for e-commerce, healthcare, financial services, and any industry where customers expect round-the-clock support.
### Consistency and Compliance
Human agents have good days and bad days. Voice AI delivers the same quality, tone, and accuracy on every interaction. For regulated industries — banking, healthcare, insurance — this consistency is also a compliance asset, as every call is automatically logged and auditable.
### Scalability Without Proportional Headcount
When call volumes spike — during a product launch, a service outage, or a holiday season — voice AI scales instantly. No recruiting, no training cycles, no overtime pay. One of the largest retail brands in Latin America reported handling **4x their normal call volume** during a major sale event using voice AI, with zero increase in support staffing.
## Voice AI Use Cases That Deliver Real Value
Not all support interactions are equally suited to voice AI. Here are the use cases with the highest automation potential and proven ROI:
### Account Inquiries and Self-Service
Balance checks, account status, subscription details, usage summaries — these are high-frequency, low-complexity calls that voice AI handles with ease. This category alone can represent 30-40% of a typical support call center's inbound volume.
### Order Tracking and Returns
For e-commerce and logistics businesses, "where is my order?" is often the single most common support inquiry. Voice AI integrates directly with order management systems to provide real-time shipping updates, initiate returns, and reroute deliveries — without human involvement.
### Appointment Scheduling and Reminders
Healthcare providers, service businesses, and financial advisors use voice AI to handle scheduling at scale. The bot can check availability, book slots, send confirmations, and make reminder calls — all autonomously. This use case has shown **40-60% reductions in no-show rates** when combined with AI-driven reminder calls.
### Payment Processing and Billing Support
With proper PCI-DSS compliance and secure data handling, voice AI can handle payment collections, past-due notifications, and payment plan arrangements. Telecom and utilities companies have deployed this at massive scale, recovering millions in delinquent accounts with voice AI-driven outreach.
### Technical Troubleshooting (Tier 1)
Guided troubleshooting for common issues — resetting passwords, restarting devices, verifying connectivity — is highly automatable via voice. When combined with knowledge base integration, voice AI can walk customers through step-by-step solutions using the same scripts your best Level 1 agents use.
## How to Deploy a Voice AI System That Customers Actually Love
Deploying voice AI poorly leads to the same customer frustration as bad IVR. Here's how to do it right.
### Step 1: Audit Your Current Call Types and Volumes
Pull 90 days of call recordings and transcripts. Categorize them by topic and resolution type. Identify which call types are: (a) high volume, (b) short average handle time, and (c) resolved without escalation. These are your automation sweet spots. Start there — don't try to automate everything on day one.
### Step 2: Design Conversations, Not Scripts
The biggest mistake in voice AI deployment is treating it like a script engine. Modern voice AI should be designed as a **conversation flow**, not a decision tree. Use real call transcripts to understand the natural language customers use. Map out multiple ways a customer might phrase the same intent. Build in graceful handling for unexpected inputs, non-sequiturs, and emotional expressions.
Work with your CX team on the bot's **persona**: name, tone of voice, pace, and degree of formality. Customers respond better to voice AI that feels human and warm — not robotic and transactional.
### Step 3: Integrate with Your Systems of Record
A voice AI bot without data integration is just an expensive FAQ. Prioritize integrations with:
- Your CRM (HubSpot, Salesforce, Zoho) for customer history and account status
- Order management or ticketing systems for real-time transaction data
- Knowledge base or FAQ database for troubleshooting and policy questions
- Calendar systems for scheduling use cases
Darwin AI's voice automation capabilities are built to integrate with major CRM platforms, ensuring every voice interaction automatically creates or updates the relevant contact record — keeping your data clean without manual input.
### Step 4: Build a Clear Escalation Protocol
Define precisely when and how the bot escalates to a human. Key escalation triggers should include:
- Customer explicitly requests a human
- Negative sentiment detected (frustration, anger)
- Bot confidence score falls below threshold on consecutive turns
- Issue type is outside automation scope (complex billing disputes, legal matters, etc.)
- Three failed resolution attempts
Ensure warm transfers include a real-time context packet — customer name, account info, call reason, and full transcript — so agents can greet the customer by name and pick up exactly where the bot left off. This single design decision dramatically reduces customer frustration at handoff.
### Step 5: Monitor, Measure, and Iterate
Voice AI is not a "set it and forget it" technology. Define your success metrics from day one and review them weekly during the first 90 days:
- **Containment Rate**: % of calls resolved by AI without human handoff. Target: 60-75% for well-scoped use cases.
- **Customer Satisfaction (CSAT)**: Post-call survey scores for AI-handled calls vs. human-handled calls.
- **Average Handle Time (AHT)**: Voice AI should dramatically reduce AHT for automated call types.
- **Escalation Rate by Intent**: Which call types are escalating most? These are candidates for improved AI training.
- **Misrecognition Rate**: How often is the bot mishearing or misunderstanding customer inputs?
Use these metrics to continuously improve your conversation flows, retrain the NLU model on misrecognized intents, and expand automation scope as confidence grows.
## Choosing the Right Voice AI Platform
The voice AI market has matured significantly. Here's a brief overview of the main platform categories:
### Full-Stack CCaaS Platforms
Genesys, NICE CXone, and Avaya offer voice AI as part of a broader cloud contact center suite. These are ideal for large enterprises that want unified voice, digital, and analytics in one platform. Implementation timelines are longer and costs higher, but the breadth of capability is unmatched.
### Specialist Voice AI Platforms
Companies like Voiceflow, Bland AI, and Vapi are purpose-built for voice AI development. They offer flexible APIs, low-code conversation builders, and deep customization. Great for technical teams that want control over every aspect of the voice experience.
### Conversational AI Platforms with Voice Capabilities
Platforms like Darwin AI that specialize in AI-powered customer engagement — combining WhatsApp, web chat, email, and voice channels — offer the advantage of unified conversation management. Customer context carries across channels: if a customer chatted with your bot on WhatsApp last week and calls today, the voice AI knows their history and can skip re-qualification entirely.
## The Human Side of Voice AI Adoption
One of the most underestimated challenges in deploying voice AI isn't technical — it's organizational. Support agents often feel threatened by automation, worrying about job displacement. The most successful deployments reframe voice AI not as a replacement for human agents, but as a tool that **elevates their work**.
When AI handles the high-volume, repetitive Tier 1 calls, human agents spend their time on genuinely complex, high-value interactions — the calls that require empathy, creative problem-solving, and relationship management. This shift improves job satisfaction, reduces burnout, and actually improves human agent retention. Companies report **25-40% reductions in agent turnover** after AI deployment, driven by the elimination of monotonous repetitive calls.
## Voice AI and the Future of Customer Experience
Looking ahead, voice AI is converging with several powerful trends that will further transform customer support:
- **Multimodal AI**: Voice interactions that can reference visual content — "I'll send you a screenshot of the error and the AI can see it while we talk"
- **Proactive Voice AI**: Outbound voice bots that proactively call customers about upcoming renewals, service disruptions, or personalized offers — before the customer has to call in
- **Emotion AI**: Real-time sentiment and emotion detection that allows the voice AI to adapt its tone, pace, and empathy level mid-conversation
- **Hyper-personalization**: Voice AI that knows your customer's entire journey — purchase history, past issues, preferred communication style — and tailors every interaction accordingly
## Conclusion: Voice AI Is No Longer Optional for Customer-Centric Businesses
In 2026, customers expect fast, accurate, and frictionless support — on their schedule, in their preferred channel. Voice AI makes this possible at a scale and cost that human-only support simply cannot match.
The businesses winning the customer experience race aren't choosing between human warmth and AI efficiency. They're combining both: letting voice AI handle the volume, speed, and consistency demands, while freeing human agents to deliver the empathy and creativity that no AI can fully replicate.
Whether you're a growing startup handling 500 calls a month or an enterprise managing 500,000, the path forward is the same: start with your highest-volume, lowest-complexity call types, deploy voice AI thoughtfully, and iterate based on real customer data.
Darwin AI can help you get there. Our conversational AI platform integrates voice, chat, and messaging channels into a unified customer engagement engine — connected to your CRM and ready to scale. [Talk to our team](https://www.getdarwin.ai) and see what modern voice AI looks like in action.
Compartir [](https://twitter.com/intent/tweet?url=&text=) [mailto:?subject=&body=](mailto:?subject=&body=)
[](https://www.getdarwin.ai/)
## Blog posts
[View All ](https://blog.getdarwin.ai/?hsLang=en)
[](https://blog.getdarwin.ai/en/support-capacity-planning-demand-spikes?hsLang=en)
[Support Capacity Planning: Handle Demand Spikes Without Hiring](https://blog.getdarwin.ai/en/support-capacity-planning-demand-spikes?hsLang=en)
Peak season doubles your ticket volume, not your headcount. The forecasting and automation math that keeps CSAT steady when demand spikes.
Lautaro Schiaffino • 13 Aug 2026
[](https://blog.getdarwin.ai/en/speed-to-lead-response-time-b2b?hsLang=en)
[Speed to Lead: Why Response Time Decides Who Wins the Deal](https://blog.getdarwin.ai/en/speed-to-lead-response-time-b2b?hsLang=en)
Most B2B teams reply to inbound leads in hours. Here is what that costs, how to measure it honestly, and how to close the gap without hiring…
Lautaro Schiaffino • 10 Aug 2026
[](https://blog.getdarwin.ai/en/average-handle-time-reduce-aht-without-hurting-csat?hsLang=en)
[Average Handle Time: How to Cut AHT Without Hurting CSAT](https://blog.getdarwin.ai/en/average-handle-time-reduce-aht-without-hurting-csat?hsLang=en)
Most AHT programs shave seconds and lose customers. Here is how to find the minutes hiding in wrap-up, hold and context - without rushing a …
Lautaro Schiaffino • 07 Aug 2026
[](https://blog.getdarwin.ai/en/customer-effort-score-ces-measure-reduce-ai?hsLang=en)
[Customer Effort Score: How to Measure CES and Reduce It with AI](https://blog.getdarwin.ai/en/customer-effort-score-ces-measure-reduce-ai?hsLang=en)
The metric that catches what CSAT misses: how to measure customer effort, read it against containment, and cut steps out of every resolution…
Lautaro Schiaffino • 06 Aug 2026
[](https://blog.getdarwin.ai/en/ai-credit-management-approve-b2b-orders?hsLang=en)
[AI Credit Management: Approve More B2B Orders, Write Off Less](https://blog.getdarwin.ai/en/ai-credit-management-approve-b2b-orders?hsLang=en)
Late payments hit a huge share of B2B receivables. See how AI credit scoring decides who gets terms, and how much, before the invoice exists…
Lautaro Schiaffino • 05 Aug 2026
[](https://blog.getdarwin.ai/en/how-to-reduce-dso-b2b-playbook?hsLang=en)
[How to Reduce DSO: The B2B Playbook for Faster Cash](https://blog.getdarwin.ai/en/how-to-reduce-dso-b2b-playbook?hsLang=en)
Global B2B DSO runs ~45 days on Net 30 terms. Here are the levers that actually close that gap, ranked by how many days each one removes.
Lautaro Schiaffino • 04 Aug 2026
[](https://blog.getdarwin.ai/en/cost-per-resolution-support-metric?hsLang=en)
[Cost Per Resolution: The Support Metric That Exposes Real Cost](https://blog.getdarwin.ai/en/cost-per-resolution-support-metric?hsLang=en)
Your cost-per-ticket number is hiding a 2.3x multiplier. Here is how to find the real cost of every problem your support team solves.
Lautaro Schiaffino • 03 Aug 2026
[](https://blog.getdarwin.ai/en/containment-rate-ai-support-metric?hsLang=en)
[Containment Rate: The Metric That Shows If Your AI Support Works](https://blog.getdarwin.ai/en/containment-rate-ai-support-metric?hsLang=en)
Most teams calculate containment rate wrong and celebrate the result. Here are real benchmarks, the three signals that expose fake containme…
Lautaro Schiaffino • 31 Jul 2026
[](https://blog.getdarwin.ai/en/sales-to-customer-success-handoff-b2b-playbook?hsLang=en)
[Sales to Customer Success Handoff: The B2B Playbook That Sticks](https://blog.getdarwin.ai/en/sales-to-customer-success-handoff-b2b-playbook?hsLang=en)
The handoff is where deal context goes to die. The brief, the five steps and the four metrics that keep renewals from quietly slipping away.
Lautaro Schiaffino • 30 Jul 2026
[](https://blog.getdarwin.ai/en/ai-order-taking-whatsapp-email-orders-erp?hsLang=en)
[AI Order Taking: Turn WhatsApp and Email Orders into ERP Data](https://blog.getdarwin.ai/en/ai-order-taking-whatsapp-email-orders-erp?hsLang=en)
Your buyers order by chat and email. Here is what it really costs to retype those orders, and how AI captures them clean the first time.
Lautaro Schiaffino • 29 Jul 2026
[](https://blog.getdarwin.ai/en/ai-chargeback-management-prevent-win-disputes?hsLang=en)
[AI Chargeback Management: How to Prevent and Win More Disputes](https://blog.getdarwin.ai/en/ai-chargeback-management-prevent-win-disputes?hsLang=en)
Chargebacks cost far more than the refund. See how AI prevents disputes, automates evidence, and recovers revenue most merchants write off.
Lautaro Schiaffino • 27 Jul 2026
[](https://blog.getdarwin.ai/en/automated-payment-reminders-invoices-paid?hsLang=en)
[Automated Payment Reminders: Get Invoices Paid Without the Chase](https://blog.getdarwin.ai/en/automated-payment-reminders-invoices-paid?hsLang=en)
59% of businesses carry overdue invoices. See how automated, conversational reminders collect the money before you ever have to chase.
Lautaro Schiaffino • 24 Jul 2026
.png)
[Try Darwin Now](https://app.getdarwin.ai/signup?landing=homepage&language=en&utm_source=organic_homepage&utm_medium=LeadGen)
#### SiteMap
- [Home](https://blog.getdarwin.ai/?hsLang=en)
- [Partners](https://www.getdarwin.ai/en/partners?utm_source=organic)
-
- [Industries](https://www.getdarwin.ai/en/industrias?utm_source=organic)
- [API](https://api.getdarwin.ai/)
- [Jobs](https://apply.workable.com/darwin-ai/)
#### Industries
- [Automotive](https://www.getdarwin.ai/en/industrias/automotriz?utm_source=organic)
- [Education](https://www.getdarwin.ai/en/industrias/educacion?utm_source=organic)
- [Real Estate](https://www.getdarwin.ai/en/industrias/inmobiliario?utm_source=organic)
- [Retail](https://www.getdarwin.ai/en/industrias/retail?utm_source=organic)
- [Health](https://www.getdarwin.ai/en/industrias/salud?utm_source=organic)
- [Insurance](https://www.getdarwin.ai/en/industrias/seguros?utm_source=organic)
- [Services](https://www.getdarwin.ai/en/industrias/servicios?utm_source=organic)
#### Recursos
- [Blog](https://blog.getdarwin.ai/en)
- [ROI Calculator](https://www.getdarwin.ai/en/roi-calculator?utm_source=organic)
- [WhatsApp Link Generator](https://www.getdarwin.ai/en/whatsapp-link-generator?utm_source=organic)
- [WhatsApp QR Generator](https://c2w.getdarwin.ai/en)
- [Help Center](https://help.getdarwin.ai/en/)
#### Legal
- [Privacy policies](https://www.getdarwin.ai/en/politicas-de-privacidad?utm_source=organic)
- [Terms of Use](https://www.getdarwin.ai/en/tyc?utm_source=organic)
© 2025, Papagaio US Corp
[](https://www.linkedin.com/company/getdarwinai) [](https://www.instagram.com/darwinai.en/) [](https://x.com/getdarwinai) [](https://www.tiktok.com/@getdarwin)
```json
{
"@context" : "https://schema.org",
"@type" : "BlogPosting",
"author" : {
"@type" : "Person",
"name" : "Lautaro Schiaffino",
"url" : "https://blog.getdarwin.ai/en/author/lautaro-schiaffino"
},
"dateModified" : "2026-04-15T12:00:00.380Z",
"datePublished" : "2026-04-15T12:00:00.000Z",
"headline" : "Voice AI for Customer Support: How to Deploy Conversational Voice Bots That Delight Customers in 2026",
"image" : [ "https://media.giphy.com/media/v1.Y2lkPTc5MGI3NjExcGU2OWFlMjY4YWJkZjQxYTgzYzE5YmY4ZDI4MDVmZGE2MDc0NjYwZiZlcD12MV9pbnRlcm5hbF9naWZfYnlfaWQmY3Q9Zw/l46Cy1rHbQ92uuLXa/giphy.gif" ],
"mainEntityOfPage" : {
"@id" : "https://blog.getdarwin.ai/en/voice-ai-customer-support-conversational-voice-bots-2026",
"@type" : "WebPage"
},
"publisher" : {
"@type" : "Organization",
"logo" : {
"@type" : "ImageObject",
"url" : "https://blog.getdarwin.ai/hubfs/Darwin%20AI%20Logo.jpg"
},
"name" : "Darwin AI"
}
}
```