The emotion model
Valence, Arousal, Dominance — a reading of the room, not a guess
Prosody scores each line of a transcript with a RoBERTa model fine-tuned on EmoBank, a research corpus of text annotated for emotional dimensions. Three numbers per line, tracked across the whole meeting.
Valence
positive ↔ negative
Whether the language is warm and constructive or frustrated and negative. A sustained dip is usually where a decision started to slip.
Arousal
calm ↔ activated
The energy behind the words. High arousal on top of low valence is the signature of a tense exchange, not just an animated one.
Dominance
in control ↔ overwhelmed
How much control a speaker sounds like they have. Shifts here surface who owned a topic and who was pushed onto the back foot.
Mood timeline
The per-line scores roll up into a timeline for the meeting. You see the shape of the discussion at a glance and jump straight to any point in the transcript.
Tense-moment detection
Where negative valence and high arousal line up, Prosody marks a tense moment. Those stretches are where decisions tend to stall, and they feed the recurring-tension view in analytics.
A fine-tuned RoBERTa model
The scorer is a RoBERTa transformer fine-tuned on EmoBank — a corpus of sentences annotated by researchers for Valence, Arousal and Dominance. Prosody runs it on its own infrastructure, so transcript text does not leave Prosody for the scoring step; the only external call in the whole pipeline is the Claude API, for drafting.
Each line comes back with three continuous scores. Those are what build the mood timeline, and what the drafting step reads alongside the words so a blocker and an aside are not treated the same way.
A signal, not a verdict
Emotion scores are an input to a human decision, never a replacement for one. They point a reviewer at the moments worth a second look; they do not decide priority, they do not assign work, and they never create a ticket. A person still reads every draft and confirms it against a real account before anything is created.
Try it
A rough, in-browser feel for the two axes that matter most. Drag either slider and watch the trace reshape.
Drag to feel how valence and arousal reshape a moment.
positive ↔ negative — how warm or hostile the language is
calm ↔ activated — how much energy is behind the words
A toy for intuition only. The real model scores three axes per line, and a reviewer still confirms every draft.