Talk to Emma, face to face.

Emma is an AI you can actually talk with. She reads your tone, expression and hesitation, and responds in real time — with a face, a voice and a personality of her own.

Meet Emma

Get the API

Runs in your browser, no download necessary

The Mission

Most of a conversation is never said. A raised eyebrow. A pause before answering. A shift in tone. People communicate constantly through everything beyond words.

Every interface in computing has moved closer to the human. We are creating a world where people can finally talk to every product, face to face.

Most of a conversation is never said. A raised eyebrow. A pause before answering. A shift in tone. People communicate constantly through everything beyond words.

Every interface in computing has moved closer to the human. We are creating a world where people can finally talk to every product, face to face.

Most of a conversation is never said. A raised eyebrow. A pause before answering. A shift in tone. People communicate constantly through everything beyond words.

Every interface in computing has moved closer to the human. We are creating a world where people can finally talk to every product, face to face.

The Full-Duplex Engine

Human conversation is a simultaneous act. You perceive while you speak, react while you listen, and respond within a few hundred milliseconds — all at once, never in turns.

Nuance Labs is building the first audiovisual model that works this way: one system that sees, hears, reasons, speaks, and expresses in the same moment, in real time.

Human conversation is a simultaneous act. You perceive while you speak, react while you listen, and respond within a few hundred milliseconds — all at once, never in turns.

Nuance Labs is building the first audiovisual model that works this way: one system that sees, hears, reasons, speaks, and expresses in the same moment, in real time.

Human conversation is a simultaneous act. You perceive while you speak, react while you listen, and respond within a few hundred milliseconds — all at once, never in turns.

Nuance Labs is building the first audiovisual model that works this way: one system that sees, hears, reasons, speaks, and expresses in the same moment, in real time.

Expressivity & naturalness

Speech and video that cross the uncanny valley

Real-time interactivity

500ms is the hard floor for conversation latency

Engaging personality

Warm, engaging, personality that is genuinely interesting to talk to

Active listening

Interjections, nodding, backchanneling — the full texture of real dialogue

multimodal intelligence

Human Foundation Model

Auto-regressive transformers learned language through next-token prediction.

The same machinery can learn human behavior—predicting the next audio and visual token instead of the next word. We're building that model.

Auto-regressive transformers learned language through next-token prediction.

The same machinery can learn human behavior—predicting the next audio and visual token instead of the next word. We're building that model.

Auto-regressive transformers learned language through next-token prediction.

The same machinery can learn human behavior—predicting the next audio and visual token instead of the next word. We're building that model.

Our Team

Built by PhDs from MIT, UW, Oxford, CMU, and Johns Hopkins—with experience from Apple, Meta, Amazon AGI, and Discord.

Fangchang Ma

Cofounder & CEO

PhD in Robotics/Machine Learning from MIT; previously an Engineering Manager at Apple.

Edward Zhang

Cofounder & CTO

PhD in Computer Graphics from the University of Washington; previously a Senior Research Scientist at Apple.

Karren Yang

Cofounder & Chief Scientist

PhD in Audio-visual synthesis from MIT; previously a Senior Research Scientist at Apple.

view full team

Our Values

Do right by people

Our commitment is to increase human well-being, and we believe AI that better understands people and communicates more naturally advances this goal.

Make Ai More Accessible

The benefits of AI should be available regardless of technical fluency. We want to enable new forms of personal expression and open up the productive uses of AI to more people.

Be honest

Nuanced AI should earn the trust that more seamless communication helps build. We want our company and products to set the highest standards for transparency.

Don't Exploit People.

We won't exploit emotional vulnerability or foster unhealthy dependency. We aim to replace mindless scrolling, not meaningful human commection.

Don't Disempower People

People should retain control over if and how AI uses their face and voice, and that permission should be well-informed. We won't sacrifice privacy or support surveillance.

Don't Deceive People

It should always be clear when you're talking to an AI, and it shuoldn't lead you to believe it's a person. It's an interface.

Talk to Emma, face to face.