PRESENSE

Real-time communication intelligence

Verbal context — synchronized with what the body actually says

Begin the Oracle Protocol

Participant session  ·  ~15 min  ·  camera + mic required

Get in touch →

Muhammad Zareii · zareii.muhammad@gmail.com

Words tell you what.
Everything else tells you the truth.

AI has learned to understand language. But human communication is never just language. Presense synchronizes the verbal stream — what is actually said, word by word — with the non-verbal signals the body emits simultaneously: prosody in the voice, micro-expressions on the face, physiological markers from video. Only when these streams are aligned can AI understand the whole human, not just the words.

💬

Verbal Context

Live transcript, keyword detection, topic tracking — the semantic layer that gives non-verbal signals meaning.

🔊

Prosody — Voice Expression

Pitch, rhythm, energy, pause patterns, filler words. The voice carries emotional signal that words alone never reveal.

🎭

Micro-expressions — Face

52 facial landmarks at 30fps, gaze direction, genuine vs. performed expression — the face that precedes the word.

💡

rPPG — Physiological Signal

Cardiovascular markers — stress, arousal, presence — read directly from video pixels. No wearable. No contact.

Three streams. One synchronized context. AI that finally understands.

Every other tool analyses signals in isolation. Presense timestamps and fuses them — what was said at the exact moment the voice wavered or the face shifted. That synchronized context is what makes AI insight genuinely meaningful.

VERBAL
💬
Live transcript Topic tracking Keywords Sentence structure
PROSODY
🔊
Pitch & rhythm Vocal energy Pauses Filler words
FACE + rPPG
🎭
52 blendshapes Micro-expressions Gaze & iris Cardiovascular
TIMESTAMP SYNC
AI CONTEXT
"At 1:42 — speaker said confident but pitch dropped 18%, voice energy halved, and a micro-expression of doubt appeared 0.3s before the word. Likely masking uncertainty."
52 Facial signals
30fps Real-time sync
0kb Video uploaded
Contexts

One platform.
Every room where communication matters.

The signals are the same. The interpretation changes with context. Presense is a platform — the analysis engine adapts to whoever is in the room.

01

Speech & Presentation Coaching

Real-time feedback on eye contact, vocal energy, filler words, and confidence arc. Post-session AI coach chat with full context of what just happened.

02

Interview Preparation

AI interviewer runs a full staged practice interview. Analyzes STAR structure, answer relevance, and non-verbal signals. Tracks progress across runs.

03

Therapy & Clinical Sessions

Therapist receives a live non-verbal feed on the patient — expression state, tension spikes, engagement drops — without interrupting the conversation.

04

Audience Intelligence

A speaker sees real-time aggregate engagement from every face in the room. Adjust pacing, energy, or content before the room is already lost.

Built in Finland by Optosense.

Optosense is a Finnish deep-tech company building at the intersection of computer vision, AI, and human communication. We are a small, focused team and Presense is our flagship product.

MZ
Muhammad Zareii
Co-founder, Optosense · Oulu, Finland
🏆 Aurora Award 2026

If you see what we're building — let's talk.

The sync between what humans say and what they actually feel is unsolved. We're building the bridge. Investors, partners, and early customers welcome.

Get in touch →