Recipe catalog / tempo-change

Steer the tempo

Should the beat slow down, hold, or speed up next, given what listeners said about pace in context and how fast recentMaterial moved?

A live loop has read chat about speed and must choose one pacing direction for the coming bars.

Explore this recipe interactively · Source and implementation guide

Use tempo-change 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 { tempoChange } from 'jev-recipes/tempo-change';

const result = await tempoChange({
  "context": "Three chat messages in the last minute: 'pick it up a little', 'faster!!', and 'this is dragging'. No one asked for it to stay slow. Stream goal: follow chat when requests agree.",
  "recentMaterial": "Slow ballad in E-flat major at about 60 bpm, half notes and quarter notes in the left hand, sparse melody, moderate dynamics, held for the last two minutes.",
  "minConfidence": 0.8
});
console.log(result);

Input contract

{
  "input": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "context": {
        "type": "string"
      },
      "recentMaterial": {
        "type": "string"
      },
      "minConfidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      }
    },
    "required": [
      "context",
      "recentMaterial"
    ]
  },
  "result": {
    "$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"
        ]
      },
      "verdict": {
        "type": "string",
        "enum": [
          "slower",
          "same",
          "faster",
          "unclear"
        ]
      },
      "confidence": {
        "type": "number",
        "minimum": 0,
        "maximum": 1
      },
      "probabilities": {
        "type": "object",
        "propertyNames": {
          "type": "string",
          "enum": [
            "slower",
            "same",
            "faster",
            "unclear"
          ]
        },
        "additionalProperties": {
          "type": "number",
          "minimum": 0,
          "maximum": 1
        },
        "required": [
          "slower",
          "same",
          "faster",
          "unclear"
        ]
      }
    },
    "required": [
      "model",
      "usage",
      "status",
      "verdict",
      "confidence",
      "probabilities"
    ],
    "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 tempo-change.

{
  "model": "demo-fixture",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  },
  "status": "ready",
  "verdict": "faster",
  "confidence": 0.9,
  "probabilities": {
    "slower": 0.01,
    "same": 0.05,
    "faster": 0.9,
    "unclear": 0.04
  }
}

Evaluation evidence

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

Limitations

• Chooses a direction only. It does not pick a beats-per-minute value or a rate of change; application code owns the amount.
• Weighs the requests stated in context as written and does not know which listeners matter more unless context says so.
• Reads recentMaterial as described; it cannot hear audio or verify that the description matches what was played.

Related recipes

• intent-change: Use intent-change to detect that a listener has changed what they want, rather than to choose a tempo direction from the whole context.
• step-progress: Use step-progress to judge movement toward a caller-defined objective rather than a tempo adjustment.