Most AI audio sounds like a robot reading Wikipedia.
Distill doesn’t.
I didn’t build a summarizer. I built a narrative engine.
Every episode is an audio essay that follows a structure to make it stick: a hook that earns your attention, a pivot that reframes the topic, the insights that matter, and a synthesis that makes it memorable.
Not bullet points. Not recaps. Storytelling you’ll remember.
Love the simplicity. I just text Distill before my jog what I want to understand next.
Aaron Sharp
Lead Learning Designer, Unity
Two tiers of audio.
Zero markup on either.
The price difference between the Text-To-Speech (TTS) models is steep, though.
Standard Tier
Clear, natural, and highly listenable. Powered by an incredibly efficient open-weights model (Kokoro 82M).
Studio Tier
Breath-takingly real. Sounds like a professional voice actor recorded it in a booth.
Have a listen
Select a topic
Episodes land in your podcast app
Add your new podcast link (RSS feed) and every future episode shows up automatically.
Pricing
Why is it ~$0.08?
Because it costs ~$0.08.
I pass through the raw API cost directly to you — to the cent.
*You’ll pay even less when cheaper models come out.
Read my short “Manifesto”FAQ
Honest answers to reasonable questions.