SEPTEMBER 2023 RELEASES
September 2023 Releases
AI Voice Tuning 101: Settings That Work Best
The tone, pace, and delivery of your AI Voice Agent directly impacts whether a contact stays on the line, engages, or opts out.
With Regal, voice configuration is a core performance lever, on par with script optimization and routing logic.
This article breaks down what voice tuning actually is, what it involves, and how different traits affect outcomes. Whether you're optimizing for conversion, retention, or simply sounding more human, this guide will show you what to adjust and why.
What “Voice Tuning” Actually Means
Voice tuning in Regal is a structured configuration process, designed to give you precise control over how AI Voice Agents sound and perform. From initial design, through testing and long-term optimization.
This is done using individual toggles for each setting within our Voice AI Agent builder.
%2520(1).png)
While Regal Voice AI Agents come with smart defaults, every parameter can be adjusted and tested at whatever level needed (and as much as needed) to perfect each use case.
We’ll take a look at each setting below and cover:
- Available tuning range
- What the extremes feel like
- Most common production settings and why
Regal’s Voice Tuning Settings
Voice Speed
Voice speed controls how fast the agent speaks. Regal supports a wide range, from 0.5 (very slow) to 2.0 (very fast). Most teams stay within the middle or moderate range (1.0-1.18) to ensure the agent sounds natural and human.
Total Available Range: 0.50–2.00
Regal Default Setting: Varies depending on agent type.
Understanding the Ranges
Slow (<1.00): Deliberate and steady. Slower speech can help improve clarity for older demographics or high-stakes conversations, but may feel sluggish for general audiences.
Slower speech can also lead to increased call duration, and therefore increased cost (at scale).
Here's an AI Agent with a voice speed setting of 0.70:
Moderate (1.00–1.18): Natural and conversational. The sweet spot for most call types. Keeps calls human-sounding and efficient. Fast enough to maintain energy, slow enough to avoid sounding robotic.
Here's an agent with the most common overall voice speed setting in Regal (1.08):
Fast (1.18+): Brisk and efficient. Great for transactional flows where speed is key (and less emotion/patience is required), or longer conversations that can run higher costs at scale. Think, collections calls, confirmations, or inbound lead capture.
This agent has a very high speed setting of 1.50:
Faster cadence (within reasonable limits) reduces dead air and shortens average handle time, which can increase throughput and lower per-call cost, but runs the risk of sounding rushed or robotic.
.png)
Voice Temperature
Voice temperature controls the variation of voice tone and expressiveness on calls. It's a subtle but powerful setting that affects emotional variability and perceived warmth/empathy.
Warmer tones (higher temperature), for example, help agents sound more human and empathetic, which is valuable in high-trust environments like healthcare, financial services, insurance, etc.
Total Available Range: 0.00–2.00
Regal Default Setting: Varies depending on agent type.
Understanding the Ranges
Low (<1.00): Consistent and flat. Best for use cases where precision and predictability matter (IVR flows, compliance language, legal disclaimers). Limits variation in tone, which can make the agent sound more robotic but reduces risk of misinterpretation.
An agent with a temperature setting of 0.50, for example, might sound something like:
Moderate (1.00–1.25): Balanced and professional. The ideal default for most calls. Adds just enough emotional variance to sound natural and expressive without losing clarity or control.
An example of the most commonly used temperature setting in Regal (1.10):
High (1.25+): Expressive and animated. Can be useful for open-ended support or conversational sales calls where emotional range builds trust. But risks sounding exaggerated or inconsistent, especially if your prompt includes strict scripting.
A high setting of 1.80 might sound like this:
.png)
Volume
Volume is straightforward, but can be important depending on the audience, their device, and their surrounding environment.
Most Regal users (86%) keep this setting at the default (1.00)
Available Range: 0.00–2.00
Default Setting: 1.00
Understanding the Ranges
Quieter (<1.00): Useful for calls that benefit from a softer tone, like when you know the caller will be in a quieter/private environment.
Moderate (1.00–1.50): Best for most use cases. Balanced, clear, and easy to understand across a range of devices and backgrounds.
Louder (1.50+): More assertive and bold. Can help in noisy environments, mobile-heavy audiences, or when the caller may be hard of hearing.
Responsiveness
This controls how quickly the agent starts speaking after the customer finishes. Lower values create longer pauses; higher values make the agent respond almost immediately.
For most users, this setting is on the higher end of the scale so conversations are well-paced and feel natural (especially combined with moderate-high interruption sensitivity).
Voice speed is used much more commonly as a control over call times.
Available Range: 0.00–1.00
Default Setting: 1.00
Understanding the Ranges
Less Responsive (<0.80): Patient and considerate. Ideal for older or slower-speaking audiences (for example, paired with certain accents or languages to match natural style). Helps prevent the AI from speaking over the customer, but may make the agent feel less dynamic to general audiences.
More Responsive (0.80+): Sharp and well-paced. Feels more real-time and efficient, while remaining natural-sounding. Can make the agent feel more “live,” but may occasionally interrupt slow speakers.
.png)
Interruption Sensitivity
Interruption sensitivity determines how easily the agent detects and stops when a customer tries to interrupt it mid-sentence.
Most Regal users (88%) stick with the default setting (0.80).
Available Range: 0.00–1.00
Default Setting: 0.80
Understanding the Ranges
Less Sensitive (<0.70): Focused and steady. Better for interactions that are more one-sided (reminders, confirmations, etc.). May ignore minor background noise and quick interjections from the caller.
More Sensitive (0.70+): Alert and reactive. Better for a more natural, conversational feel. Higher sensitivity means the AI will “listen” better on calls, letting callers interject freely.
Very high sensitivity (0.95+) introduces the risk of false pauses to background chatter or other non-communicative sounds made by the caller.
.png)
Accent Selection
Accent isn’t a slider, but is part of your voice selection. This can impact regional trust and engagement, and make callers feel more comfortable. It’s great for local services.
Most Regal users stick with Neutral American voices across all call types.
Voice Fallback and Other Settings
Beyond these settings, there are additional structural settings that improve the reliability and perceived personality of your AI Agent.
Voice fallback settings ensure resilience in the rare case of provider outages, so even if your primary TTS provider goes down, the agent continues without interruption. Regal supports automatic fallback routing across providers like ElevenLabs, OpenAI, and Cartesia. More on that here.
Silence handling controls whether the agent fills gaps in conversation or waits patiently, impacting how talkative or reserved the agent feels during calls.
Voicemail detection ensures your agent doesn’t waste time talking to a machine, or delivers the right pre-scripted message once voicemail is reached.
While subtle, these settings can meaningfully influence how the agent is perceived, especially depending on how they are paired with tuning parameters like speed, tone, and responsiveness.
Voice Settings Directly Impact Performance
Each voice setting can directly impact how an AI Agent is perceived—how human they sound, how naturally they interact, and how well they contain and drive specific outcomes.
Certain characteristics predictably influence caller behavior
Human-likeness improves long-term trust and reduces opt-outs after the initial greeting.
Familiarity matters. Callers are more likely to stay engaged with voices that sound like them demographically or regionally.
Natural tone and pace helps calls feel lifelike and keep them moving steadily, increasing both comprehension, comfort, and caller agreeability.
Voice settings work together as well, not in isolation:
- High responsiveness combined with moderate-high temperature gives the impression of an agent who’s present and engaged.
- Low-Moderate voice temperature and lower interruption sensitivity can reinforce authority and composure, projecting confidence and professionalism without sounding harsh.
- Low-Moderate voice speed, less responsiveness, and high temperature would come across as more delicate, or an agent that’s a better “listener.”
What Regal’s Production Data Shows
While there are certainly edge cases (i.e. slower voices for older audiences), in general, Regals production data shows that you want voices to sound natural and approachable. That means a natural tone, steady pace, with moderate warmth.
When in doubt, use a female voice: 78% of companies using Regal use female voices (across all use cases), which tend to test higher for warmth and approachability.
For Lead Qualification and Collections Agents, that number goes up to 90%.
What voice should I choose for my Voice AI Agent?
Your AI Agent’s Voice Is a Performance Lever
In the end, the right combination of speed, temperature, responsiveness, and interruption handling makes all the difference in how your agent is perceived and how well they perform.
With Regal’s production data, smart defaults, and expert support, fine-tuning your agent’s voice to match your audience, use case, and brand tone is well within reach.
Latest Blog Posts
%20(1).png)
June 2025 Releases
June’s releases give you more control to test, improve, and scale AI agents—while also making life easier for human agent teams. From real-time debugging tools to capacity control and a floating Chrome extension, we’re unlocking faster workflows, better control, and stronger performance across the board.
.png)
Caller ID vs. CNAM vs. Branded Caller ID: What’s the Difference?
Caller ID, CNAM, and Branded Caller ID all help identify an incoming call and, therefore, increase call answer rates. Find out how they differ and how outbound phone sales teams can utilize each to reach prospects and customers effectively.
.png)
%20(1).png)
%20(1).png)
%20(1).png)
%20(1).webp)
.avif)
.png)
The Automated Phone System Revolution: Why 73% of Enterprises Are Getting It Wrong (And How to Get It Right)
Explore how automated phone systems are transforming enterprise communication strategies. Learn how to avoid common pitfalls, optimize customer journeys, and achieve ROI through strategic deployment across industries like healthcare, insurance, and education.
%20(1).png)
.png)
.webp)
.webp)
.webp)
.webp)
.webp)
.webp)
.webp)
.webp)
How are Generative AI Voice Agents Different from AI Voice Assistants?
When it comes to comparing AI Agents vs. AI Assistants, Siri & Alexa handle simple tasks, but Gen AI Voice Agents—like Regal’s AI Phone Agent—drive real business impact with human-like conversations, automation, and seamless integration.
.webp)
.webp)
%20(1).webp)
7 Best Use Cases for AI Voice Agents in Your Contact Center
As AI technology continues to evolve, the use cases for AI Voice Agents in contact centers will only increase. By answering these six key questions, you can identify where AI agents fit best today in your contact center and plan for future integrations.
.webp)
.webp)
.webp)
.webp)
%20(1).webp)
.webp)
%202.webp)
AI Agents for Education: 8 Use Cases for More Meaningful Student Outcomes
AI Agents for Education are transforming student engagement—boosting enrollment, improving retention, and making support more human. Discover 8 game-changing use cases that free up your staff while delivering better student outcomes.
Regal Named One of Forbes America’s Best Startup Employers 2025!
Regal is officially one of Forbes America’s Best Startup Employers 2025, ranking #164 out of 500. This recognition is a testament to our incredible team, our innovative work culture, and our unwavering commitment to advancing AI technology.
AI in Education: The Future of Student Engagement & Enrollment
AI in education is helping to streamline admissions, automate student engagement, and enhance higher ed outreach. Discover key education technology trends to boost enrollment and learn why automated student engagement tools are the future.
.webp)
.webp)
.webp)
.webp)
.webp)
.avif)
.avif)
5 Ways to Improve Agent Productivity & 5X Outbound Performance
In this blog, we share tips to improve agent productivity for handling high volumes of calls, whether it's inbound support teams or outbound sales teams. The guiding principle is simple — focus your agents on tasks that absolutely requires their attention, and automate everything else.
.avif)
8 Strategies to Improve Call Answer Rates by 40%
Discover 8 proven strategies to improve call answer rates by 40%. Learn how personalized outreach, Branded Caller ID, and AI-driven solutions can transform your outbound contact center and boost engagement. Increase your call answer rates and drive more revenue today!
.avif)
.avif)
Insurtech Insights: How Regal Drives Revenue Across the Policy Lifecycle
Our Co-Founder & CTO, Rebecca Greene, delivered a presentation at the recent Insurtech Insights NYC 2024 event about how insurance brands can meet the moment of global uncertainty and rebuild trust by turning untapped customer data into personalized, revenue driving conversations across the Policyholder lifecycle.
.avif)
Beyond CCaaS: How to turn your Contact Center into a Revenue Center
Why are so many contact centers stuck being cost centers? Why do they keep looking for cost reductions instead of revenue increases? Bad data and technology decisions are at the core of this issue. We need "marketing automation" (aka unified customer profiles, event-driven systems and a/b testing) like Regal.io in the contact center to empower teams to start looking for incremental revenue instead.
Treat your customers like royalty
Ready to see Regal in action?
Book a personalized demo.
Thank you! Click here if you are not redirected.
Oops! Something went wrong while submitting the form.
