# CassetteAI Music Generator - Core.Today AI API

> CassetteAI's fast, low-cost music generator via fal.ai. Produces 10 to 180 seconds of music from a text prompt at under one credit per second. Returns a WAV file.

- **Provider**: CassetteAI
- **Model ID**: cassetteai/music-generator
- **Category**: Audio & TTS
- **Credits**: 47 per 60s (0.775 credits per second of duration)
- **Speed**: Fast
- **Quality**: Standard

## Features
- Cheapest music model on the platform — 0.775 credits per second
- 10 to 180 seconds per generation
- Fast turnaround for drafts and loops
- WAV output

## Use Cases
- Background music for prototypes and games
- Quick mood sketches before a premium model
- Loops and beds at scale

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - The prompt to generate music from (genre, mood, instruments, tempo)
- **duration**: integer - Duration of the generated music in seconds (10-180). Billed per second

## Examples

### Core.Today theme (instrumental)
The same company-theme prompt given to every instrumental model — compare the results side by side
```json
{
  "model": "cassetteai/music-generator",
  "input": {
    "prompt": "Upbeat K-pop electro-pop company jingle instrumental, 128 BPM, synth brass stabs, punchy drums, bright synth lead, catchy hook, fun and playful",
    "duration": 30
  }
}
```

### Lo-fi beat
A 30-second chill lo-fi loop
```json
{
  "model": "cassetteai/music-generator",
  "input": {
    "prompt": "Chill lo-fi hip hop beat with warm piano chords, vinyl crackle and a laid-back drum groove",
    "duration": 30
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- duration is required — 10 seconds is the minimum, 180 the maximum
- Expect instrumental output; vocals are not a strength of this model
- Use it to iterate on mood cheaply, then move to Lyria or ElevenLabs for the final