Small decisions. Interesting possibilities.Submit contentSubmit
Data & analysis

talkr

today i built talkr, a speech analyzer using @typesafeai > talkr gives you a topic > you talk about it for 30s > jev analyzes your speech: pauses, filler words, repetitions, confidence, clarity > you get a score and feedback to improve can’t wait to 10x my speaking skills

Added to Jevfast
X post ↗

How it uses Jev

Talkr gives the speaker a topic, records a 30-second response, and uses Jev to analyze pauses, filler words, repetitions, confidence, and clarity. The analysis produces a score and feedback.

App workflow

  1. Give the speaker a topic

    Give the speaker a topic.

  2. Capture a 30-second response

    Capture a 30-second response.

  3. Use Jev to analyze speech characteristics

    Use Jev to analyze speech characteristics.

  4. Return a score and improvement feedback

    Return a score and improvement feedback.

Why it is interesting

The app turns a short speech sample into several dimensions of feedback for practice.

  • X Scanner

    Label visible X posts with typed Jev judgments about promotion, engagement prompts and information density.

  • Jgrep

    Filter lines and records with natural-language predicates and Jev probabilities.

  • Jsort

    Rank text on a natural-language criterion using pairwise Jev judgments and a fitted statistical scale.

Explore more in Data & analysis →