Sohri – Turn short stories into binge-able audio episodes
Hey HN, I love creating, and I've been fascinated by AI audio tools. But as a creator, trying to actually use them felt like a trap. First, wrestling with raw TTS APIs to create something that doesn't sound like a robot reading a phone book is an art form in itself. It takes forever to get the pacing and tone right. Second, and this was the real deal-breaker: even if you create a masterpiece, platforms like YouTube feel like they're just waiting to demonetize you or slap a restriction on your work because it's "AI-generated." It feels like you're building on someone else's land, and they can…
In plain words
Sohri is a platform that converts short stories into audio episodes using AI text-to-speech technology. It's designed for creators who want to produce natural-sounding audio content without wrestling with technical APIs or worrying about demonetization on mainstream platforms. The service handles pacing, tone, and delivery automatically, allowing creators to focus on storytelling rather than audio engineering or algorithmic restrictions.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I love creating, and I've been fascinated by AI audio tools. But as a creator, trying to actually use them felt like a trap. First, wrestling with raw TTS APIs to create something that doesn't sound like a robot reading a phone book is an art form in itself. It takes forever to get the pacing and tone right. Second, and this was the real deal-breaker: even if you create a masterpiece, platforms like YouTube feel like they're just waiting to demonetize you or slap a restriction on your work because it's "AI-generated." It feels like you're building on someone else's land, and they can change the rules overnight. It's soul-crushing. I wanted a sanctuary for audio creators. A place that’s more like a recording studio in your pocket than a frustrating API wrapper. A platform where you can focus on your story, not on fighting the tools or the distribution algorithm. So, I built Sohri (https://sohri.ai). Sohri is designed to turn your short stories into polished, binge-able audio episodes, handling the boring parts so you can be the director. During testing, I was surprised to find that for many shorter pieces, the AI narration actually felt more engaging than my own quick recordings because it never gets tired or stumbles. It’s free to use, and the core features will always be free. My goal is to build a place where creators can experiment, share their work, and eventually earn a living without fear. I’m here all day to answer any questions. I'd be incredibly grateful for your feedback—try listening to a story or creating your own and let me know what you think.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064The 1st Agentic Canvas for building apps visually with AI
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
- TY
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
- DA
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
Dev tools · 2025 · drawafish.com
