Valoquent: Craft Conversation
A live feedback loop for the way you think out loud. Real conversations with figures from history, scored as you talk on clarity, depth, follow-through, and presence. The conversation is the lesson. The meter is how you see it.
The Conversation Meter
A live meter on screen scores your conversation as you speak. 22 behavioral signals per utterance: depth, follow-up, reciprocity, on-topic coherence, constructive challenge, troll detection, flow streak, vocabulary, balance, and twelve more. Sub-millisecond updates, on the same screen as the avatar. Three zones, five states: Surface, Exploring, Engaged, Deep Dive, Flow State. Asymmetric momentum smoothing means bad turns hurt faster than good turns help. Built on Ghazarian et al. (AAAI 2020), validated at 0.85 correlation with human judgment.
Three-tier Memory Architecture
Each character remembers what you talked about and brings up unfinished threads through structured memory, and archival storage. Returning users start at tier-appropriate scores.
Two-axis Disclosure System
16 distinct relationship states per character. Global trust tier (guarded, warming, open, vulnerable) intersects per-topic depth (surface, candid, deep, raw). Three-layer gating: turn count, signal strength, and meter score must all align before a tier advances.
The Tapestry
A constellation map of every topic you've explored with each figure. The deeper you go, the more the Tapestry reveals.
Mind Levels & Arc Score
Mind Levels move with your average score across all conversations: Novice, Curious, Thinker, Scholar, Intellectual, Sage. Arc Score is the per-session number, calculated from four factors: Conversational Arc, Depth of Exchange, Engagement Quality, Vocabulary Richness. Relationship depth advances per figure: Acquaintance, Familiar, Conversant.
Seven-level Flow Economy XP Progression
Curious to Luminary. Built on Self-Determination Theory (Deci and Ryan): autonomy, competence, relatedness. Progression rewards depth, not session count.
The Conversation Guide
An in-app explainer for everything the meter measures. Five zones with ranges and accolades. Four Arc Score factors. Six Mind Levels. Three relationship-depth stages. Nothing about the scoring system is hidden.
Custom Intelligence Layer Per Character
Hand-built character by character, refined across hundreds of calibration runs. Aurelius does not sound like Curie. 150+ vocabulary terms per character. Each anchored in their own primary sources: Einstein from his 1905 relativity paper and the Einstein-Szilard letter, Curie from her radium memoir, Aurelius from his Meditations. The knowledge base is curated, not generated.
Music Grounded in Learning-environment Research
Home-screen ambient regulates arousal between sessions, sequenced across multiple tracks to prevent habituation. Post-session chimes timed to the zone reveal.
Calibration Discipline
Calibrated against a 48-scenario battery across three training tiers: local pipeline, production harness, full production.
Security & Privacy
Your conversations are yours. Full account deletion, GDPR-compliant data export, secrets handling, and Apple JWT authentication are in place. SOC 2 controls in flight.
Nothing Here is Improvised
Grounded in 30+ peer-reviewed studies in conversation, learning, and honest design. Every part of the app, from the meter to the memory to the music, is anchored in published research.
Free: 30 credits (about 5 minutes of conversation) with access to all available features for every user, no sign up needed!
Starter - $5.99/mo: 360 credits per month (~60 minutes of conversation), auto-renewing monthly until canceled
Pro - $14.99/mo : 1,200 credits per month (~200 minutes of conversation), auto-renewing monthly until canceled
Terms of Use (EULA): https://lanternworks.dev/terms
Privacy Policy: https://lanternworks.dev/privacy
Security: https://lanternworks.dev/security
Refund: https://lanternworks.dev/refund
Show more
Show less
