Human AI Agents have a real face and a real voice, and run live conversation rather than turn-based exchange. Interrupt mid-sentence, trail off, talk over it, and the endpointing holds. Setup is one still photo, a persona and a voice. No rig, no capture session, no script. Two face models behind a single API. Portrait for scale, Presence for expressiveness. Both drop into Pipecat and LiveKit. Try to interrupt it. Most demos cannot survive that, and it is the fastest way to judge this one.
I have sat through a lot of AI demos where the face looks perfect but the conversation is unstable.
You say something, it waits. You pause to think, it talks over you. You interrupt, and it finishes its sentence anyway.
Everyone nods and nobody says the obvious thing, which is that this is not a conversation.
So we built Human AI Agents.
What it is
One still photo, a persona written in plain language, and a voice. You get an agent you can talk to and interrupt.
What runs underneath
Two face models behind a single API. Portrait for speed and scale, Presence for expressiveness. Both stream over WebSocket and drop into Pipecat or LiveKit.
What we actually spent the time on
Turn-taking. Knowing when someone has finished a sentence rather than paused to think. It is the unglamorous part and it is most of the product.
Try to break it. Interrupt it mid-sentence, talk over it, trail off, use an accent, most of all have fun!
Real-time voice makes $/minute tempting, but I’d rather know cost per completed call outcome. A 4-minute call that books the meeting can be cheaper than a 60-second call that goes nowhere.
Turn-taking being most of the product is the right admission, and it's also the thing nobody buys on. We work on the generated side of avatars and the failure mode is different, a face that holds for eight seconds and falls apart on the ninth, but the rule is the same, the boring temporal part is where the work actually is. I'd put endpointing latency on the page next to the face model specs, because two face models behind one API reads like the differentiator and it isn't. Anyone who has shipped voice will pick you on the interrupt handling.
Congrats on the launch! I use LemonSlice right now but am always open to new providers. Do you have a differentiator?
Proud and honored to be a part of the Ojin team. Hard work do pay off. Congratulations to everyone at Ojin. My favourite is Presence. 🤩
We're very excited to share Ojin today. Please check it out and share your feedback, thoughts and questions. We're eager to hear what you think - the more feedback, the better!
I'm very excited to finally have Ojin released!! A lot of engineering efforts went into making this product possible and I'm so proud of the team. Can't wait for people to try it out!
Happy to have contributed to this as a product engineer. It's been a wild few months of building, and it's great to finally see people trying what we made. Huge respect to the team, genuinely talented and great people to build with. Let's go! 🚀
So happy to see Ojin out today after all the hard work! Proud to work with this team 🔥
Congrats on the launch! ✨ Got some nice recommendations from Sofia for travelling and it continues the discussions pretty smoothly when interrupted or when I interject something randomly (and knows to respond to that also). It still is obvious that it's an AI, but the experience is pretty good.
About Ojin on Product Hunt
“Talk to an AI Agent with a real face and voice, in real time”
Ojin launched on Product Hunt on August 27th, 2026 and earned 105 upvotes and 20 comments, placing #16 on the daily leaderboard. Human AI Agents have a real face and a real voice, and run live conversation rather than turn-based exchange. Interrupt mid-sentence, trail off, talk over it, and the endpointing holds. Setup is one still photo, a persona and a voice. No rig, no capture session, no script. Two face models behind a single API. Portrait for scale, Presence for expressiveness. Both drop into Pipecat and LiveKit. Try to interrupt it. Most demos cannot survive that, and it is the fastest way to judge this one.
Ojin was featured in Artificial Intelligence (477.4k followers) on Product Hunt. Together, these topics include over 117.7k products, making this a competitive space to launch in.
Who hunted Ojin?
Ojin was hunted by Mio. 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 Ojin stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Mio
Hi Product Hunt. I am Mio, founder of Ojin.
I have sat through a lot of AI demos where the face looks perfect but the conversation is unstable.
You say something, it waits. You pause to think, it talks over you. You interrupt, and it finishes its sentence anyway.
Everyone nods and nobody says the obvious thing, which is that this is not a conversation.
So we built Human AI Agents.
What it is
One still photo, a persona written in plain language, and a voice. You get an agent you can talk to and interrupt.
What runs underneath
Two face models behind a single API. Portrait for speed and scale, Presence for expressiveness. Both stream over WebSocket and drop into Pipecat or LiveKit.
What we actually spent the time on
Turn-taking. Knowing when someone has finished a sentence rather than paused to think. It is the unglamorous part and it is most of the product.
Try to break it. Interrupt it mid-sentence, talk over it, trail off, use an accent, most of all have fun!
I'll be around all day.