SEPTEMBER 2023 RELEASES
September 2023 Releases
How to Choose a Text-to-Speech Provider for AI Voice Agents in the Contact Center
Building an AI voice agent for a contact center requires more than just selecting a great-sounding voice. Your text-to-speech (TTS) provider plays a crucial role in ensuring natural conversations, low latency, and high reliability. But choosing the right text-to-speech provider for AI voice agents isn’t just about voice quality—it’s about selecting the right tool for the specific job, whether it’s an IVR replacement, outbound sales call, support call, or collections call.
In this blog post, we’ll explore:
- How AI voice agents work
- Key factors to consider when selecting a text-to-speech provider for AI voice agents
- Which provider is best for different use cases
- Why flexibility in your AI platform is critical
Why AI Voice Agents Rely on the Right TTS Provider
A contact center AI voice agent operates in a real-time conversational loop:
- Speech-to-Text (STT): The AI listens to the customer and converts their speech into text.
- Large Language Model (LLM): The AI determines the appropriate response based on context.
- Text-to-Speech (TTS): The AI converts the response back into spoken audio using a TTS engine.
This loop must be as fast as possible to maintain a smooth, real-time conversation. While TTS providers alone typically operate around 300ms, factoring in speech-to-text (STT), LLM processing, and telephony, the total response time is usually in the range of 800–1200ms. The TTS provider plays a critical role in delivering a clear, natural voice as quickly as possible, making latency and quality key factors in choosing the right provider.
Key Factors in Choosing a TTS Provider for AI Voice Agents
These following are the factors Regal considered when deciding which TTS providers to incorporate into our AI Agent Platform. Note: we’re not considering price here because all of the TTS providers are competitive on price within reason, and the price will continue to come down. The assumption here is that we’re applying AI Voice Agents to conversations that are currently being done by humans, and therefore picking the best TTS provider is better than the cheapest.
1. Voice Quality, Naturalness & Backchanneling
Voice quality determines how natural and engaging your AI voice agent sounds. A well-tuned voice can improve customer experience, reduce frustration, and create a more human-like interaction. Some TTS providers offer backchanneling support, allowing the AI to interject with sounds like "uh-huh," "got it," or "I see" to create a more fluid, natural conversation.
Not all TTS providers optimize for real-time contact center conversations—some focus more on voices for creative applications like audiobooks, video voiceovers, and dubbing. For contact centers, the most important factors are:
✅ Natural intonation – Does it mimic real human speech?
✅ Emotion & expressiveness – Can it shift tone based on context?
✅ Backchanneling support – Does it enhance conversational flow?
We’ve found that ElevenLabs, Play.ht, and Rime all offer a subset of voices optimized for contact centers, with ElevenLabs having the largest library of realistic voices. OpenAI serves as a great backup provider, while PolyAI and Google voices sound more voice-assistant-like and Deepgram’s voices are far too robotic for this use case (but cheap).
2. Voice Consistency & Predictability
Voice consistency ensures that the AI delivers responses predictably. Inconsistent output can make interactions feel unnatural or erratic. Interestingly, when prospects demo Regal AI Voice Agents, they tend to prefer expressive voices, but when deploying in real contact center environments, they prioritize consistency over expressiveness.
- ElevenLabs: Most human-like but highly variable—may say the same sentence differently each time. Lowering the temperature reduces variability.
- Rime: Trained on contact center recordings, making voices less expressive but highly consistent—great for IVR replacements where branding and pronunciation stability are critical.
- Cartesia & Play.ht: Offer fine-tuning for stability, though voices are less high-quality than ElevenLabs or Rime.
- OpenAI: Feels more “voice of the future” (ala the movies Her) but lacks intonation and predictability controls.
3. Customizability
Customization allows businesses to refine the voice agent’s tone, style, and pronunciation. Some providers offer voice cloning, SSML support, and phonetic control to enhance flexibility.
- Voice Cloning: ElevenLabs, Rime, Play.ht, and Cartesia support cloning your best agents’ voices for AI deployment. (However, this adds latency.)
- SSML & Pausing: Most providers allow basic inline tags for controlling speech cadence (e.g., "Hello there!<break time='500ms'/> How can I assist you today?")
- Phonetic Control: Rime & EleveLabs go one step further by providing strong pronunciation dictionaries for technical terms & brand names, increasing correct articulation of key words. ElevenLabs supports IPA and CMU. Rime allows you to generate custom pronunciation for specific words and to specify a disambiguated variant for homographs e.g., ("I like fresh produce_noun” vs. “They produce_verb a wide array of home goods for decorations.") None of these approaches are 100% yet.
4. Latency, Stability & Real-Time Performance
Latency is the delay between input and response. Lower latency improves real-time interactions, while higher latency makes the AI seem slow.
Most TTS providers now offer similar average latency, but the consistency of latency varies:
- OpenAI & ElevenLabs: Cloud-based APIs with variable response times. Latency fluctuates depending on traffic.
- Play.ht & Cartesia: On-prem solutions provide stable, low-latency performance.
Rime: provides an on-prem option, however, the company itself is not yet as well funded or established as the other providers.
5. Language & Accent Support
If your contact center serves global audiences, language and accent support is crucial. ElevenLabs offers the most natural multilingual voices (and they have a community library with voices from many accents), while Play.ht supports the widest range of languages.
Summary Comparison of Top Text-to-Speech Providers for AI Voice Agents in Contact Centers
Choosing the Right Provider for Different Use Cases
So with all of these considerations, which is the right text-to-speech provider for AI voice agents at your company? That really depends on your use cases. Contact centers can use multiple TTS providers, assigning different ones to different types of calls for better engagement and cost optimization.
Final Thoughts: Why Flexibility is Key
At Regal, we understand that no single TTS provider is perfect for every use case or stable enough to rely on just one. That’s why we offer multiple providers that excel at different things – ElevenLabs, PlayHT, OpenAI – giving contact centers the flexibility to:
✅ A/B Test Multiple Providers – Easily compare voice quality, latency, and performance.
✅ Use Different Voices for Different Use Cases – Choose the best provider for IVR, sales, support, or collections.
✅ Support Backup TTS Providers – Prevent outages by automatically switching to a secondary or tertiary provider when needed.
Ready to build a high-performance AI voice agent for your sales and support interactions? Click here to learn more about our AI Agents or click here to reach out to Regal.ai today to see how we can power your contact center with the best AI voices in the industry!
.png)
Latest Blog Posts
.jpg)
.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.
.jpg)
.png)
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.
.jpg)
.jpg)
.jpg)
.jpg)
.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)
.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)
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.
.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.
The Next Step Forward in AI will come from Consumer Businesses
Consumer businesses are implementing AI-enabled customer experiences without any change in behavior on the part of consumers, which is leading AI to become common with more speed than past transitions like the internet and the smartphone. And it means that the next step in AI will not come from the LLM providers. The next big step forward in AI rests in the hands of consumer businesses.
Innovating on Patient Care | B2C Sales Podcast Episode 7
Explore Eric Hauser's remarkable career journey from GovTech to healthcare disruption at Cadence, highlighting the transformative power of innovation, collaboration, with a special focus on the pivotal role of Regal in driving patient engagement and outcomes.
How SoFi, Perry Health & Allstate Personalize CX at Scale
Discover how Regal.io's AI-powered personalized outreach solutions are revolutionizing outbound sales and customer experience across industries like healthcare, finance, and insurance in our latest eBook, "Modernizing Outbound Contact Centers: How to Treat Millions of Customers like One in a Million."
.jpeg)
Introducing Collaboration-Native Features to CCaaS
Combining collaboration functionality into CCaaS workflow tools invites more cross-functional users from a company to participate in designing the end-customer experience, leading to better omni-channel orchestration and customer outcomes. Learn more about Regal's collaboration features.
How Regal.io is Turning the $40B CX Industry on Its Head
Jon Heaps, former VP, Channel at Observe.ai, Talkdesk, and inContact interviews Alex Levin, Co-Founder & CEO of Regal.io, about the history of the contact center industry and some of the key challenges teams making outbound calls face as customers demand more online experiences.
New SMS & Branded Caller ID Rules Are Enhancing Customer Experience
Are you using Branded Caller ID for outbound calls or SMS? New SMS and Branded Caller ID regulations rolled out in Q2 2023 that you MUST KNOW ABOUT. The new regulations require that every company register their SMS campaigns and Branded Caller ID campaigns before being allowed to send texts or brand calls.
Announcement: Regal Conversation Intelligence
Regal’s Conversation Intelligence drives higher conversion rates for B2C sales teams. We use both the traditional QA/coaching tools, and brand new conversational triggers that allow you to update customer profiles and send automated follow up messages based on what is said in a conversation.
Supercharge Customer Engagement with the Regal & Braze Integration
Existing B2C sales, service, and retention teams can now leverage Braze’s cross-channel messaging capabilities with Regal’s outbound phone & SMS sales platform to personalize their outreach, drive better customer outcomes, and ultimately generate revenue for the business.
How Regal Helps Consumer Lenders Achieve Growth in Tough Times
Our Co-Founder & CTO, Rebecca Greene, spoke with journalist Tony Zerucha at the recent Fintech Nexus USA 2023 event about how consumer lenders are using personalized phone and SMS sales outreach to obtain growth despite high inflation and rising interest rates.
Meet Regal Call Branding™: Branded Caller ID for 400M+ US Devices
We are excited to announce Regal Call Branding™ including Branded Caller ID. Available on all 400M wireless devices in the US (as well as most of Canada and the UK), Regal Call Branding™ puts you in control of what people see when you call their cell phone – including showing your brand and/or logo.
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.
