If you listen to a lot of podcasts, there’s a chance you’ll remember funny facts and wonder… “Wait, who talked about eating sriracha fries?” or more serious questions. To find the answers, you must first find the podcast and then search through their transcripts. Dexa tries to make podcast search easier by leveraging artificial intelligence.
The tool lets you ask questions about a single podcast, like Andrew Humberman’s Huberman Lab podcast in the screenshot below, or ask all podcasts in Dexa’s database — there are currently more than 120 with more being added. The search results will give you an AI-generated summary of the answer along with pointers to podcasts where the participant discussed the topic.
For example, you can ask questions like “What’s the best way to get more sleep?” and find answers to this from Dexa’s podcast library with time-stamped links to these conversations. You can also @mention a specific podcast to narrow down your search results.
Image Credits: Dexa
When I asked Dexa “What does Mark Zuckerberg think about Threads?” returned the results of his chat on Lex Friedman’s show about the social network. But it also showed me results where podcast hosts were talking about Mark Zuckerberg’s comment about Threads on another platform.
You can also share these searches and results with others via links. Because of this, Dexa is also able to index some of the content for search engines like Google.
The company
Dexa was started by Riley Tomasek in 2023, who previously co-founded an app called Flight so users can capture notes, images, and ideas on different boards and collaborate on them. The company was acquired by Figma in 2021.
Tomasek said he was indeed in good health. As part of the knowledge building phase, he listened to the Huberman Labs podcast. She wanted to take a supplement suggested by Huberman but forgot the dose. So he started looking for when the neuroscientist talked about it and the process took a long time.
“After that experience, I decided I’m going to make something to make it easier because I don’t want to go through that process again. So I transcribed all the episodes and used tools like OpenAI integrations and Whisper to make the search work and published it on X,” said Tomasek.
After Tomasek posted about his tools, Huberman retweeted it, and that generated inbound interest from podcasters and listeners to develop the tools. He said many podcasters talked about people not being able to find certain content.
The startup uses different indexing techniques combined with a knowledge graph of people, episodes and shows to enhance its search. Tomasek said the tool was launched nearly nine months ago and has answered over 1 million queries with 50,000 people visiting the site each month.
Dexa has raised $6 million in seed funding led by Abstract Ventures and The General Partnership with participation from Maple VC and Guillermo Rauch. The company currently has three people on the team and now plans to hire more engineering staff.
The company is launching a redesigned website and announcing a partnership with Huberman Labs where Dexa’s search will be integrated into the podcast site. For this, the startup has trained a special model — think of it as GPT in ChatGPT.
The new design allows users to ask follow-up questions and allows them to monitor the connected conversation without having to leave the window.
Future road map
Dexa’s growth has been mostly organic with podcasters referring people to the tool. He said this method still has momentum as the company works with popular podcasters. Therefore, it is not currently seeking to invest in the approach.
“We tried podcast advertising for a while and found that our efforts resulted in a relationship where we indexed their content, added it to Dexa, and they started talking about it organically,” he said.
The company isn’t currently making money, but has considered both subscriptions and advertising as sources of revenue as it scales.
Dexa also plans to create a mobile app where it can increase consumption of podcasts through short clips. Additionally, the company plans to introduce account creation so users can save their searches.
Opportunities and challenges
There are many tools included Riverside, Podcastle and MusixMatch that help podcasters with transcription. As for the search, the recently rotated Very Disco it tries to become a kind of podcast on IMDB with information such as books, people and TV shows mentioned in the podcasts.
MusixMatch chief product officer Marco Paglia sees promise in what he calls Dexa’s “assistant-driven UX.” Additionally, he believes there is potential to allow people to retrieve a particular person’s views through podcasts. But his reason for not incorporating such a search into MusixMatch is that he believes that text is not the best way to interact with LLMs.
“I feel that typing in a chat is not the best UX for assistants. Instead, for this use case I strongly believe that voice is the future,” he said.
Ben Cmejla, a partner at The General Partnership, believes Dexa’s approach to using knowledge from creators for search is unique.
“The success or failure of a platform will depend on the trust it builds with users and content partners. Dexa’s approach puts trust first – users’ trust that their questions are answered by human experts, and partners’ trust that their content will be seen and not just used for training data or anonymous summaries,” he said.
