The production layer for AI voice
Built by the people who measure it. Onepin orchestrates today’s best voice models, validates every output, so you can ship audio that’s ready to publish.
Why teams trust Onepin
Every output is validated.
Onepin checks each generation before it ships, so there are no surprises in production.
Proven in evaluation.
We built Podonos, the evaluation infrastructure used to score and compare speech-AI systems. We don't just hope a voice is good — we define how “good” is measured.
Built by specialists.
Our team comes from Google, DeepMind, Sony, Carnegie Mellon, and Georgia Tech — and we built the evaluation infrastructure the industry uses to score AI voice.
Model-agnostic by design.
We route to the best model available for your use case, so you're never betting the quality of your product on a single vendor.
What we believe
We’re building the future of AI voice across all human languages.
Measured, not guessed
Proven with data, not claimed.
Models aren't the bottleneck
The craft is using them well.
Voice for every language
Not English-only.
Sweat the last 5%
Demos are easy. Shipping isn't.

Note from the founder
During the pandemic I tried to turn the books I loved into audio I could actually listen to. The technology was supposed to be ready. It wasn't. Voices mispronounced names, flattened the emotion, and fell apart the moment a sentence got complicated. In English it was frustrating. In my own language, and in most of the world's languages, it was far worse.
The surprising part is that the models were never the problem. Today's voice models are extraordinary. The gap is in everything around them: picking the right one, guiding it, and checking that what comes out is genuinely good enough to publish. That layer barely existed, and the moment to build it is now.
So we did. We started Podonos to measure voice quality at scale, and Onepin is what we built on top of it: the layer that turns great models into voice you can ship, in any language.
Our vision is simple. Production-quality voice for everyone with something to say, in the language they say it in.
Soohyun Bae (SB)
Founder & CEO

Built with expertise from
Ready to publish?
Turn any script into production-quality voice, in any language, in minutes.
Run your first line