Recipe catalog / lyric-mood-fit

Check lyrics against the mood of the music

Do lyrics fit the mood and pacing of the music described in music?

You generate, suggest, or review lyrics for a described track and want to catch lines whose mood or pacing clashes with the music before showing them to a writer.

Explore this recipe interactively · Source and implementation guide

Use lyric-mood-fit in TypeScript

Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.

import { lyricMoodFit } from 'jev-recipes/lyric-mood-fit';

const result = await lyricMoodFit({
  "lyrics": "Hands up, we don't stop till the sun comes up\nBass in the trunk and the whole crew showed up\nNo sleep tonight, turn the lights down low\nOne more round and then we go, go, go",
  "music": "Slow, sparse piano ballad in D minor at 62 bpm with long sustained chords and a single cello line, written to underscore a grieving scene in a short film.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "lyrics": {
        "type": "string"
      },
      "music": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "lyrics",
      "music"
    ]
  },
  "result": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "model": {
        "type": "string"
      },
      "usage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          },
          "output_tokens": {
            "type": "integer",
            "minimum": 0,
            "maximum": 9007199254740991
          }
        },
        "required": [
          "input_tokens",
          "output_tokens"
        ],
        "additionalProperties": false
      },
      "status": {
        "type": "string",
        "enum": [
          "ready",
          "review"
        ]
      },
      "probability": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "verdict": {
        "type": "string",
        "enum": [
          "fits",
          "clashes"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "probability",
      "confidence",
      "verdict"
    ],
    "additionalProperties": false
  }
}

Saved example result

This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo lyric-mood-fit.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "probability": 0.04,
  "confidence": 0.96,
  "verdict": "clashes"
}

Evaluation evidence

Use the evaluation guide to measure this decision on your own labeled cases.

Limitations

• Judges mood and pacing fit only. It does not check rhyme, syllable count, meter, or whether the lyrics scan against a melody.
• The music is known only from its description; the verdict cannot hear the track.
• Does not judge lyric quality, originality, or whether the lyrics are appropriate for an audience.

Related recipes

• audience-fit: Use audience-fit to judge whether content suits a described audience, rather than whether lyrics suit a described piece of music.
• certainty-match: Use certainty-match for the analogous check that the confidence of a statement matches its evidence.