MasterClass brings AI instructors to life with ElevenLabs
Chapters6
Introduction to On Call where users can get personalized advice from top instructors by voice, turning prior practitioner knowledge into coach like guidance.
Masterclass’s on-call feature turns practitioners into AI coaches, using ElevenLabs to deliver real-time, personality-rich voices from Gordon Ramsey, Cuban, and more.
Summary
Mundar Babay of Masterclass explains how GenAI voices fill a long-standing user request: to talk directly with instructors beyond watching classes. Masterclass’s new on-call product extends their core model—where experts teach via high-quality video—to provide personalized, time-bound coaching from trusted sources. ElevenLabs enables this by delivering high-fidelity, persona-driven voices with low latency, making AI-driven conversations feel natural and trustworthy. The team experimented with chat-first interfaces before integrating lifelike synthetic voices, recognizing that voice brings personality, humor, and immediacy to coaching. From Day One, the collaboration with ElevenLabs focused on voice quality, latency, and a tight partnership spanning 18 months, with hands-on data curation and model tuning. The on-call ecosystem also explores role plays with figures like Mark Cuban and Chris Voss, expanding from one-off questions to structured coaching scenarios. Babay emphasizes that users want personalized, applicable advice—something traditional search or generic AIs can’t reliably deliver—and ElevenLabs helps Masterclass deliver that trusted, real-time connection. The result is a richer user experience where a single nagging problem in the kitchen or a business challenge can be addressed through a trusted instructor’s voice, transforming knowledge into applicable guidance. Masterclass’s broader mission remains democratization of expert knowledge, now extended through AI-driven, on-demand coaching channels that feel human, timely, and dependable.
Key Takeaways
- Voice quality from ElevenLabs is “night and day better,” enabling authentic instructor personas with appropriate pacing and subtle humor.
- Latency of the AI voices is a standout feature, delivering real-time responses that feel as natural as speaking with a human coach.
- The on-call product has evolved from chat to voice-first interactions, delivering higher engagement and perceived trust through personalized coaching from real-world experts.
- Role plays (e.g., Mark Cuban, Chris Voss) are being curated at scale, enabling thousands of coaching scenarios with professional and personal-use cases.
- The collaboration includes deep data curation and model-tuning work with ElevenLabs, spanning 18 months of joint development and ongoing support.
Who Is This For?
This is essential viewing for product leaders and developers at educational platforms who want to add trusted, AI-powered coaching with authentic voices. It showcases how to balance quality, latency, and trust when turning practitioners into AI coaches.
Notable Quotes
"when the genai voice came on the on the horizon we're like okay, we think this is the missing piece."
—Babay notes the moment the team realized AI voice could fulfill an unmet need for instructor interaction.
"So with on call you can get on call with Gordon get on call with him."
—Illustrates the product idea: direct access to expert voices for personalized coaching.
"the quality of the voice is just like night and day better, right?"
—Highlights ElevenLabs’ impact on voice fidelity and personality.
"Even now almost 90% of the conversations are voice... Voice has that magic that brings the experience the personality"
—Shows user preference for voice interactions over chat and the value of vocal personality.
"we have stood up a product area where we just have a lot of curated role plays... thousands of them."
—Describes expansion into role-play coaching scenarios with famous figures.
Questions This Video Answers
- how does Masterclass's on-call feature work with ElevenLabs AI voices?
- what makes ElevenLabs voice synthesis suitable for coaching conversations in education tech?
- can AI coaches like Gordon Ramsay or Mark Cuban actually replace human instructors in Masterclass?
- what are the latency benchmarks for real-time AI voices in customer-facing apps?
- how does data curation and model tuning improve AI coaching quality on Masterclass?
MasterclassElevenLabsGenAI voiceon-callAI coachingvoice synthesisGordon Ramsay AIMark Cuban AIChris Vossrole plays
Full Transcript
when the Genai voice came on the on the horizon, we like okay, we think this is the missing piece. I'm Mundar Babay. I'm chief product officer at Masterclass. Our mission at Masterclass is to democratize access [music] to the knowledge of the world's best. Uh we do that with classes, with video classes. Um [music] and that across the entire body of spectrum like from the artists to sports uhmen to business leaders across the across the spectrum. And one of the things that we consistently heard throughout our lifetime was our users really wanted to talk to our instructors um about going deeper into a topic or asking follow-up questions.
Um [music] and that's the part where before Gen AI it was not scalable all the solutions that we came to the table with. Um but with Gen AI it actually become a reality that we could we could bring to our users. So we have been on that journey for some time now with our new product called on call and [music] yeah it's been fun. So with on call the as I mentioned the idea is um you can take a class or you can just get go directly to on call and you can get personalized advice from the world's best again like with masterclass core product we trans transformed the best of the world from practitioners into teachers.
Uh with on call we are transforming them from practitioners or teachers into coaches and [music] advisers. So you can with on call you can get on call with Gordon Ramsey and get all your cooking questions answered that matter to you. If you're in the kitchen you're cooking something and you have that one nagging problem you can call Gordon get on call with him. Uh if you have a business problem you can call Cuban and talk to Cuban about things. So [music] yeah it's it's all about enriching our users lives by giving them moment in time advice from very trusted sources.
What we heard consistently was users were like hey I learn a lot from the classes our classes people absolutely love them right and they are great production quality great knowledge like they are the best vehicle we have um at our hand to really impart the knowledge what users wanted was I get all the knowledge but then I have certain problems that are quote unquote like very personal to me or unique to me and I want to engage with someone who really understands the problem and they're like when I engage with an AI, I don't know if I can trust this a generic AI.
When I go and engage or if I just Google search, I'll need to find out the information that I can really genuinely trust and applicable to my use case or my problem. Whereas if I have a business problem [music] and I know let's say the Cubans AI is created with Cuban, I know that I can trust the source of [music] the information that it is coming from. Um so we actually tried many vendors. um the the stuff that I would say 11 really shined on two main [music] vectors. One is the quality of the voice is just like night and day better, right?
Uh and that's where given that it matters so much to bring the personality out like the tone of the voice the pacing like all of that is super critical because people can can easily detect and we want to make sure like for example with Gordon's AI there is little bit of humor programmed into it too and it is able to like the voice is really able to bring it out. Um so I would say quality of the voice. Second one is the latency it's brilliant. Uh how how quick the voice gets produced in real time.
And third one is just the partnership with 11 has been phenomenal like from every step of the way for past 18 months. Uh you guys have helped us out. So yeah let's say those three. So we started off with just having a chat [music] interface a chatbot like interface and that worked but it it was missing the magic a little bit. Um so the next step was to create chat interface with instructors uh for instructors uh and same thing it worked well people got value but like it felt like the magic is missing. Uh and when the genai voice came on the on the horizon we're like okay we think this is the missing piece.
Um so then we built it uh with 11 as our key partner and it's been a phenomenal journey uh building the product with 11 but the pipeline is like the the standard speech to text LLM [music] and then 11 at the back end. Um but yeah like the experience is as good as you pick up your phone and you have a problem and you call Cubid. We thought chat will be the part that will get most adoption. [music] Even now almost 90% of the conversations are voice even though it's like higher barrier for people than chat.
Voice has that magic that brings the experience the the personality on of the instructor really alive and it has worked wonders for us. We are also venturing into the land of role plays. Like one of the use cases that came up organically is we saw a lot of users engaging in role plays with a Mark Cuban or with a Chris was about negotiation. So we have stood up a product area where we just have a lot of curated role plays like thousands of them. uh users can engage in professional role plays, personal role plays and then get coaching [music] from the Mark Cuban or the Chris Voss or the others of the world.
Deeply we integrated 11's team with our engineering and product teams uh to again train the voice models to literally you guys helped us with like curating the data and like cleaning up the data and giving us pointers [music] on these are the aspects you may want to watch for when you're thinking about what data sets to create has been phenomenal partnership. So,
More from ElevenLabs
Get daily recaps from
ElevenLabs
AI-powered summaries delivered to your inbox. Save hours every week while staying fully informed.




