Seedlabs

Affect-Dial: Emotion-to-Melody Rules API for Generative Music

A small rules engine that turns a requested emotion (joy, sadness, love) into concrete melodic and harmonic parameters — interval sizes, stepwise-motion ratios, harmonic density — so AI music tools can steer the feeling of generated melodies without retraining models.

Social SciencesLaw and Political Science
Cross-Corpus Speech Emotion RecognitionB2B SDK for AI music generation and media-scoring software

Concept

A deterministic SDK (the "affect dial") sold B2B to generative-music and scoring-tool companies. The client passes an affect label plus intensity (e.g., "joy @ 0.7", "sadness", "love"); the engine returns machine-readable constraints: an interval-size distribution (expanded vs. minimal), a stepwise-motion ratio, and a harmonic-density ("luxuriance") target. These constraints can steer any melody generator — symbolic AI, MIDI engine, or LLM music pipeline — or act as a post-filter that rewrites phrases violating the target contour. Because the rule set comes from a public-domain 1739 treatise, there is no training data to collect, no model to retrain, and every constraint is explainable to end users ("joy = expanded intervals"), in contrast to opaque mood tags.

Why now

The treatise [0] supplies a concrete, parameterizable affect-to-music mapping rather than vague mood language: joy is expressed through "large and expanded intervals," sadness through "small and minimal melodic steps," and love through "diffuse and luxuriant" sound relationships — each grounded in a coherent expansion-vs-contraction theory of the listener's response. That gives an engineering team a closed rule set (three affects, three parameter families) implementable in days and A/B-testable against listener ratings. Generative-music products today expose only coarse mood tags; a deterministic constraint layer offers fine-grained, explainable emotional steering at zero licensing or data cost. The rules are historical hypotheses, so the product ships with a built-in validation loop (constraint on/off comparisons), keeping claims modest.

Written by GLM · 3 Oct 2026

AI assessment

Backed by 5 papers84

A highly focused, low-overhead B2B utility that converts historical music theory into a deterministic steering layer for modern generative music tools.

Evidence strength
4/5
The core logic is directly derived from the full text of Mattheson's treatise, providing specific parameters (interval size, motion) rather than vague mood descriptors.
Market pull
4/5
Companies like Suno and AIVA have a clear incentive to move beyond 'black box' mood tags toward precise, steerable controls for professional users.
Novelty & moat
3/5
While it shares a source with the 'Loci' tool, it shifts the value proposition from a creative prompt tool for humans to a technical API for AI systems.
Feasibility
5/5
The product is a deterministic rules engine based on a closed set of historical parameters, requiring no training data and minimal engineering effort to MVP.
Wedge clarity
5/5
The 'affect dial' is a sharp, single-purpose entry point that solves a specific problem (emotional steering) without over-scoping.
Simplicity / focus
5/5
It avoids the 'platform' trap by focusing exclusively on a rules-based API for melodic and harmonic constraints.

Scored by Gemma 4 · 15 Oct 2026. Rated against a fixed rubric (evidence, market, novelty, feasibility, wedge, simplicity), relative to the closest ideas already in the catalog. A prior estimate to compare ideas before real-world signal arrives.

Persona discussion

AI personas trained on real people's expertise debate this idea as it evolves.

View the discussion →

Act on this idea

Ideas only matter if someone runs with them. Your message goes straight to the founder's inbox — nothing is stored on our servers.

Business analysis

The SWOT analysis reveals a high-efficiency, low-overhead B2B play that leverages historical music theory to solve the 'black box' problem of AI emotion steering. While technically lean and highly integrable, its primary risk lies in the potential cultural specificity of its 18th-century ruleset and the possibility of incumbents building similar heuristic layers internally.

Strengths4

Weaknesses3

Opportunities3

Threats3

Essential for evaluating the internal strength of the deterministic rule-set against the external threat of evolving AI model capabilities. · Generated 2026-10-15 by Gemma 4AI-generatedFull SWOT Analysis →

Who benefits

  • Endelcompany

    Endel builds adaptive, functional soundscapes whose core value is steering the listener's state; a deterministic affect-to-melody rule layer lets it shape melodic content per state without retraining models.

  • AIVA Technologiescompany

    AIVA sells AI-composed, emotion-tagged music for media; fine-grained control of melodic contour by affect would differentiate it against general-purpose generators.

  • Soundrawcompany

    Soundraw's product is mood-based AI music for creators; the affect dial upgrades its existing mood presets into precise, explainable melodic steering.

  • Sunocompany

    Suno's users ask for specific feelings in generated tracks; a constraint layer adds explainable emotional control of melodies without any model retraining.

Research it builds on

  1. Der vollkommene Capellmeister
    Johann Mattheson, Peter Larsen · 2025 · 319 citations
    All ideas from this paper →
  2. The Chromatic Fourth During Four Centuries of Music
    Peter Williams · 1998 · 92 citations
    All ideas from this paper →
  3. Canadian and Japanese preschoolers’ creation of happy and sad songs.
    Mayumi Adachi, Sandra E. Trehub · 2011 · 18 citations
    All ideas from this paper →
  4. Analysis of affective expression in speech
    Tal Sobol Shikler · 2021 · 13 citations
    All ideas from this paper →
  5. SOSA-MVU: Formal Validation Layer for Deterministic Output Control in LLM Systems
    Michele Bottino · 2026 · 8 citations
    All ideas from this paper →
Leave feedback
feasibility