SB here, founder of Onepin. Our launch goes live on Saturday at 12:01 AM PT. I want to use this thread to learn how you work, not to pitch.
Here is what we keep seeing. A team generates 1,200 lines of AI voice for a product video, an ad campaign or a course. The voice sounds great. Someone listens to the first twenty lines, nods, and ships the rest on trust. Line 1,200 reads the product name from its spelling, and the customer is the first one to hear it.
We spent two years at Podonos measuring how AI voices sound, with 150,000 human listeners doing the rating. The voices got the delivery right. What kept failing was names, prices and dates, and the only check most teams had was one person with headphones.
So, honestly:
1. Do you listen to all of it, some of it, or none of it before it goes out?
2. What has slipped through? A brand name, a number, a date, your own company's name?
3. If a check existed that caught those before you published, what would it have to get right for you to trust it?
I'll answer every reply here, before and after launch day. If you want to hear what the check catches, onepin.ai runs one line without an account.
Hey Product Hunt π SB here, founder of Onepin. Thanks @rohanrecommends for hunting us.
A great AI voice reads "Porsche Taycan" as TAY-can. Porsche says TIE-kahn. It guessed from the spelling, and nobody caught it, because nobody listens to line 1,200.
We spent two years at Podonos measuring how AI voices sound, with 150,000 human listeners doing the rating. The models solved delivery. What kept failing was names, prices and dates, and the only check most teams run is a person with headphones.
Today we're launching Onepin, the production step after text-to-speech. It runs on the voices you already use, ElevenLabs, OpenAI, Google and 30+ more, and checks every line before it ships.
Here is what it does to every script:
π’ Spells out prices, dates and abbreviations before the voice reads them.
π Checks names, brands and drug terms against a 4-million-word pronunciation dictionary.
π Scores every line for naturalness, clarity, word accuracy and pronunciation, against a bar you set.
π§ Fixes the one wrong word in the same voice, without re-rendering the take.
Two decisions we made on purpose. Onepin checks how a name was said, not just what the transcript spells. And there is no box where you type phonetic spellings: the dictionary and the fix do that work, so your script stays as written.
Built for anyone shipping AI voiceover at volume: product videos, ads, explainers, dubbing, audiobooks, courses, and platforms that put a voice in front of millions of users. API, SDK and MCP from day one. SOC 2 Type II.
You keep your voice. Onepin makes sure it says the right words.
Free to start, no card: onepin.ai. You can run one line on the homepage without an account.
Try it and tell me what's missing, here or at sb@onepin.ai. We'll be in the comments all day, answering questions and running your lines. π
π LAUNCH SPECIAL: 20% off for Product Hunt users through October 31. The code is under the 20% off badge above.
One question for you: what's the word your AI voice keeps getting wrong? Run it on onepin.ai (free, no card), switch the run to shareable, and paste the link below so everyone can hear the before and after. I'll reply to every one. No time to sign up? Drop the word and I'll run a few today.
The drug terms in the 4M-word dictionary caught my eye. I'm building a voice AI that phones elderly parents every day, and the failures that hurt trust most are exactly this kind: a medication name or a family member's name said slightly wrong, and an older listener stops believing the call is from someone who knows them. Question: does the pronunciation check work on short, live-generated lines (a few seconds, no time to re-render), or is it designed for batch scripts like videos and courses? And can a user pin a custom name, like a grandchild's, so it is always said right?
@igorgurovichΒ Great question: for a full transparency, we have been focusing on the accuracy while sacrificing the latency. Our roadmap is to make AI accurate first and then to make them fast. I have been hearing from numerous voice AI agent companies that the errors on critical terms are deal breakers, we are working toward making them possible. Technically, it is called a distillation (or teacher-student network) where a big neural network teaches a small one that typically runs fast, we are on this. Please contact me directly.
@soohyun Voice AI checking names and prices before speaking sounds really useful for avoiding mistakes
@shivam_kushwaha16Β Thanks. Mainly two things: making the script to be well spoken by AI, which is called normalization. Also, checks for the pronunciations and auto fix, where our internal models reviews the pronunciations and fix them. Please try!
does it automatically detect accents when fixing a single word o do we need to manually adjust the pitch?