Built with AI on Replit: WhisperAI automates Google Drive transcription
Eman Khoubian is Founder & CEO of WhisperAI, a transcription platform that layers advanced prompting, custom vocabulary, speaker labeling, bulk workflows and a developer API on top of speech-to-text. She built the product using AI tools in Replit and is piloting an integration with Google Drive to automate entire transcription workflows, moving beyond the simple transcript most competitors deliver.
Give AI the technical heavy lifting – WhisperAI handed transcription to AI and is prioritising AI-driven discovery – but keep humans leading content, product judgement and customer-facing work. Launch early, listen to users, fix problems fast and iterate rather than waiting for perfection.
What’s the quick origin story of your business, and what makes what you do genuinely different from the other options your customers are looking at?
WhisperAI.com started because I saw a gap between how powerful AI transcription had become and how basic most transcription products still were.
I’m not a traditional software engineer, but I built WhisperAI entirely with AI, using Replit, and turned it into a full transcription platform.
What makes us different is that we go beyond speech-to-text with advanced prompting, custom vocabulary, speaker labeling, transcription styles, AI tools, bulk workflows and our developer API. We’re also building an integration with Google Drive to automate the entire transcription workflow, an industry first.
Most competitors just give users a transcript. We’re building everything around it.
Where does most of your new business come from today, and where do you wish it came from?
Most of our new business today comes from organic search and AI channels. We’re now investing heavily in AI search visibility as traditional organic search traffic continues to decline. That’s where I expect more of our growth to come from going forward.
What’s one thing you’ve actually handed over to AI in the last year, and one thing you tried it on and went back to doing the human way?
We’ve handed transcription and our speech-to-text engine completely over to AI. It’s faster, more accurate, scalable and more cost-effective than doing it manually.
Content is different. I’ve tried relying heavily on AI for content creation and management when we first launched, but I went back to having humans lead it. AI is useful for research and drafts, but I still think humans are better at knowing what’s actually worth saying.
Have you noticed a change in how customers find you or what they already know before they reach out? Is anyone arriving through AI assistants like ChatGPT yet?
Yes, we’re definitely seeing more customers come through AI platforms like ChatGPT. It’s still early, but the trend is clear. We’re also an early customer of the OpenAI Ads platform, so we’re actively testing and measuring how AI-driven discovery converts compared to traditional search.
If you were advising someone in your industry on all of this for the next 12 months, what would you tell them to actually do, and what would you tell them to ignore?
Focus on the customer. Make the product easier, better and more affordable, and listen closely to what users are actually asking for.
Especially early on, I’d ignore the desire to make everything perfect before launching. Bugs will happen. Customers understand that. What matters is how quickly you fix problems, adapt and keep improving the product based on real feedback.
Thank you to Eman Khoubian and the team at WhisperAI for sharing what actually worked with Leaders Perception readers.
Want to share your playbook?
Leaders Perception publishes founder and operator interviews every week. A few questions, about five minutes, no calls. It is free and everyone we accept gets published.