Product Thumbnail

Onepin

AI voiceover with every name, price and date said right

Developer Tools
Artificial Intelligence
Audio
Visit WebsiteSee on Product HuntTwitter ⧉

Hunted byRohan ChaubeyRohan Chaubey

AI voices sound human now. But they still guess names from the spelling, and nobody has time to listen to every line. Onepin runs on the voices you already use (ElevenLabs, OpenAI, Google, 30+ more), spells out prices and dates, checks names against a 4M-word pronunciation dictionary, scores every line, and fixes the wrong word without re-rendering the take. Built for teams shipping AI voiceover in several languages: product videos, dubbing, courses. Free to start, no credit card required.

Top comment

Hey Product Hunt 👋 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:
🔢 Spells out prices, dates and abbreviations before the voice reads them.
📖 Checks names, brands and drug terms against a 4-million-word pronunciation dictionary.
📊 Scores every line for naturalness, clarity, word accuracy and pronunciation, against a bar you set.
🔧 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. 🚀

🎁 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.

Comment highlights

porsche as TAY-can lol 😂 finally someone fixing the names and prices thing. works with elevenlabs voices too?

Using ElevenLabs on a client project, and I have to say I never seem to catch everything before I publish. It seems long overdue that something like this would be used to rate accuracy.

I conduct classes in three languages, and it is in the dates and prices that my AI voice becomes confused. It would be interesting to know how Onepin deals with the currency symbols in various locales.

I have used AI voiceovers before and have never made it past the first minute of listening. Just Taycan alone sold me on this.

Part of my time during last year was spent designing pipelines for TTS to create product videos, and the pronunciation quality assurance part was something that we never managed to solve, we accepted a certain level of error and continued. It makes sense to have a tool that is designed especially to fill the gap between "the voice sounds human" and "the voice speaks the right words".

From experience working at agencies that provide bulk-generated voiceover AI for clients, the worst nightmare one can have is the mispronunciation of the client’s company name in their own advertisement. This is one of the worst mistakes that could happen. A software that identifies this mistake automatically, without human intervention, would transform our level of trust in bulk-generated voiceover AI.

Founder’s post on forums about how we should be missing something is a great start, it’s almost like a public bug bounty for pronunciations. My answer: internal codenames and acronyms used in our products that sound just fine when written but mispronounced in all available TTS voices because they are not listed in any dictionaries.

I run a product video pipeline where the biggest issue is not creating the voice but rather QA-ing it. No one has the time to check 1,200 lines of text in their entirety and simply sample the first 20 lines. This solves the real problem and not the fancy one.

I work as an English dubbing professional for a mid-sized SaaS firm. The number one complaint from our foreign clients who do not understand English is that the names of features are mispronounced in such a way that they cannot be pronounced in the same way as their phonetics. I am going to test a couple of those in the free trial version now.

They say it fixes words without having to re-render the whole take.. Patching audio always leaves behind weird sounds. I guarantee the background noise changes completely when that one fixed word gets dropped into the timeline. It’s just not smooth. You can hear it.

I do the voiceover work for a small advertising agency and we call our silent killer 'dates.' "03/04" was misread in two different markets last quarter. Interested to know how Onepin deals with locale-specific dates.

Can you correct individual words without changing the rest of the audio? Congrats team!

I have experienced firsthand the exact situation that you have described, a video for a class that had the name of one of the students mispronounced because no one bothered to go through the important words list to check if it contained names not listed there. Scoring each line of dialogue is the answer, not a quicker way to do the manual checking.

Being able to catch and fix those small mistakes without re-rendering everything sounds genuinely useful, especially for teams producing content in multiple languages.

Congrats, Soohyun. I ship short product videos with AI voiceover and the pronunciation check is the step I do by ear today, so I will try this. Thanks a lot.

Any suggestions if I am already using ElevenLabs?

the naming problem is real, we deal with the same thing on live calls at Dial. the difference for us is latency, we can't check and re-render before the line ships because there's no "before" at all, it's a live turn. is Onepin scoped to pre-rendered scripts where you have time to check first, or could the pronunciation dictionary and scoring run fast enough to sit in a live TTS path too

@soohyun Great to see a tool that focuses on accuracy, not just voice quality. Does it support multiple languages?

About Onepin on Product Hunt

“AI voiceover with every name, price and date said right”

Onepin launched on Product Hunt on October 10th, 2026 and earned 443 upvotes and 80 comments, earning #1 Product of the Day. AI voices sound human now. But they still guess names from the spelling, and nobody has time to listen to every line. Onepin runs on the voices you already use (ElevenLabs, OpenAI, Google, 30+ more), spells out prices and dates, checks names against a 4M-word pronunciation dictionary, scores every line, and fixes the wrong word without re-rendering the take. Built for teams shipping AI voiceover in several languages: product videos, dubbing, courses. Free to start, no credit card required.

Onepin was featured in Developer Tools (521.6k followers), Artificial Intelligence (481.7k followers) and Audio (2.2k followers) on Product Hunt. Together, these topics include over 225.3k products, making this a competitive space to launch in.

Who hunted Onepin?

Onepin was hunted by Rohan Chaubey. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.

Want to see how Onepin stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.