Meet Raven.
It's perception
–not just vision.

Raven-0 is a perception system that doesn't just see, it understands, making conversations feel natural, and deeply human.

Sign Up for Free

See Docs

▋

input

Raven-0

‍If AI is going to understand humans, it needs to see and reason the way we do.

Traditional affective computing approaches based on systems like FACS reduce human expression to a rigid handful of categories—happy, sad, neutral—assigning percentage scores to emotions. But real emotions don’t fit into checkboxes.

Emotion isn’t a checklist—it’s fluid, layered, and deeply tied to context. A polite smile isn’t real joy. Frustration can look like confusion. A flicker of doubt can disappear in an instant. Humans express themselves fluidly, shaped by context, memory, and nuance. Humans express themselves fluidly, shaped by context, memory, and nuance—not in neat, isolated snapshots. So why should AI try to understand them that way? That’s why we built the world’s first contextual perception system.

Meet Raven-0, the only perception system that allows machines to see, reason, and understand like humans, all in real-time.

Emotional Intelligence

First of its kind, this model interprets emotion in natural language, noting intent, body language, and nuances in expressions only a human would notice.

Ambient Awareness

Continuously detects presence, environmental changes, and key actions, providing real-time background context to enhance conversations.

Callout Key Events

Watches out for any specified gesture, object, or behavior, and triggers function calls when detected.

Multi-channel

Just like a human, Raven-0 sees and processes screensharing and other visual inputs to ensure complete understanding.

“Integrating Raven-0 into ACTO’s platform enables real-time analysis of facial cues and contextual signals during patient interactions with healthcare professionals. This enhancement allows ACTO to deliver more adaptive, intelligent, and personalized experiences for patients, ultimately improving engagement and decision-making in the healthcare sector.”

Kumar Erramilli

CTO at ACTO Health

Build smarter AI with customizable perception

Prompted vision

Tell Raven-0 exactly what to look for—track objects, detect gestures, or monitor UI elements with simple prompts for passive monitoring to suit your use case.

Seamless, instant perception

Easily activate Raven-0 with a single parameter and instantly enhance conversations with real-time perception

Custom automations

Trigger tool calls and automate actions with Raven-0. Works with or without a custom LLM, with built-in visual memory to keep interactions context-aware and efficient.

See Developer Docs

AI perception transforms real interactions

Raven-0 unlocks a depth and quality of interaction, previously not achievable in AI systems

Raven works in concert
with our other models

Raven-0 works alongside our models to enhance vision, interaction, and contextual understanding.

Replica Model

Phoenix-3

The most advanced full-face rendering model ever built, Phoenix-3 generates lifelike digital replicas with natural facial movements, micro-expressions, and real-time emotional response—making AI feel truly present.

Learn more

Turn-Detection Model

Sparrow-0

AI that understands the rhythm of conversation. Sparrow-0 analyzes tone, pacing, and intent to engage naturally, pausing, interrupting, and responding with human-like timing.