Catch the Full Episode:
Episode overview
Voice agents are quickly transitioning from new tools to revenue infrastructure. Instead of serving as a glorified talking FAQ, today’s AI voice systems can serve as qualifiers, programmers, concierges, boarding guides, retention reps, and sales assistants.
In this episode of the Duct Tape Marketing Podcast, John Jantsch interviews Ryan Mrha, founder of Yodify, a platform that enables creators and brands to stay connected to a degree with AI-powered voice and text agents trained on content libraries.
Mrha explains why purpose-built voice agents are outperforming traditional AI tools, how multi-layered LLM reduces false positives, and where businesses can start safely experimenting with voice AI. The discussion explores the future of consumer behavior, the role of AI in modern marketing processes, ethical transparency considerations, and practical implementation strategies for agencies and creatives alike.
If you want to know where voice AI fits into your marketing, sales, or customer experience strategies, this episode brings you both insight and practical guidance.
About Ryan Mrha
Ryan Mrha is the founder of Yodify, a platform that helps creators and brands maintain personal engagement at scale. Yodify allows fans to call or text an AI agent that speaks in the creator’s voice, based on their existing content library.
By combining voice synthesis, multi-layered LLM orchestration, and structured agile engineering, Mrha focuses on building purpose-driven AI agents that feel authentic, align with the brand voice, and can perform specific business roles.
He is also involved in launching Methodiq, a platform focused on AI-powered motivational experiences.
Key Takeaways
1. Voice Agents from Novelty to Revenue Infrastructure
Businesses should stop thinking of voice AI as a talking FAQ and start treating it as a role within the organization, such as a business development advocate, onboarding assistant, or planner.
2. Standard AI Tools Deliver Bad Results Without Role Design
Simply loading the knowledge base and telling it to “act like John” produces inconsistent results. Active voice agents need to:
- Defined job descriptions
- Multiple LLM levels planned
- Targeted commands for specific regions or roles
- Access to structured information
3. Multi-LLM Architecture Reduces Ideas
Instead of relying on one big notification, Yodify breaks tasks into targeted LLM calls, such as orchestration, action execution, and response execution. This improves accuracy and reduces the risk of hallucinations.
4. Consumer Behavior is Changing
Modern consumers prefer:
- Do some independent research
- Avoid premature sales negotiations
- Get involved only when it is close to making a decision
Voice agents can provide 24/7 answers without hard selling, aligning perfectly with this changing consumer mindset.
5. Transparency Can Be a Competitive Advantage
There is still disagreement about whether users feel “cheated” when talking to AI. However, positioning the voice agent further as an “AI advisor” may improve trust and adoption.
6. Start Small with Clear Use Cases
The best way to use voice AI is through a focused, low-risk pilot:
- Receptionist agent
- Scheduling an appointment
- Simple eligibility call flow
- One LLM basic knowledge test
Start small. Prove the ROI. Then expand.
7. Voice AI Is Especially Important for Creators
As creators scale, personal interaction becomes impossible. Voice agents allow fans to text or call an AI trained on the creator’s content, maintaining communication while increasing engagement.
Best Moments From The Episode
- 00:03 Voice Agents as Revenue Infrastructure
John outlines the transition from new AI to active, role-based AI agents. - 01:12 What is Voice Agent Actually?
Ryan explains how voice agents combine LLM’s responses with text-to-speech tools. - 02:23 Why “Load All” Fails
A discussion of why abandoning the library in LLM produces negative results without systematic planning. - 03:42 Role-Based AI vs Emotional AI
Clarifying that active agents are built for business roles such as sales, support, and concierge, not emotional ones. - 07:11 AI in the Modern Buyer’s Journey
It examines how voice agents can change the original calls. - 10:18 Do Customers Feel Cheated?
Ethical and experiential implications of AI transparency. - 12:08 Creating a purpose-built agent
Ryan explains how projects start with small, focused use cases. - 13:30 AI Receptionist Use Case
Why simple use cases like editing can deliver immediate value. - 18:54 Safe Pilot for the Marketing Agency
How agencies can test AI voice agents without major risk.
Memorable Quotes
- “Voice agents go from youth to revenue infrastructure.” John Jantsch
- “If you’re clear about what you want the LLM to do, you’ll get the best results. It won’t do too much at once.” Ryan Mr
- “People don’t want to be sold, they want to ask their questions.” Ryan Mr
- “There’s no point in building something your customers don’t want.” Ryan Mr
