# ElevenLabs Music - Core.Today AI API

> ElevenLabs Music via Replicate. Composes a song from a text prompt with a target length of 5 seconds to 5 minutes, optional vocals, and MP3 / WAV output. Billed per second of the requested length — a 10-second clip costs about 190 credits.

- **Provider**: ElevenLabs
- **Model ID**: elevenlabs/music
- **Category**: Audio & TTS
- **Credits**: 193 per 10s (19.3 credits per second of music_length_ms)
- **Speed**: Medium
- **Quality**: High

## Features
- Per-second billing — pay only for the length you request
- 5 seconds to 5 minutes per song
- Vocals or forced instrumental
- MP3 (128/192 kbps) or WAV up to 44.1 kHz

## Use Cases
- Short jingles and stingers priced by the second
- Ad and short-form background music
- Full songs with vocals up to 5 minutes

## 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 - Description of the music you want to generate (genre, mood, instruments, tempo, vocals)

### Optional
- **music_length_ms**: integer (default: 10000) - Target duration in milliseconds (5,000-300,000). Billed per second of this value
- **force_instrumental**: boolean (default: true) - If true, removes vocal elements from the generated music
- **output_format**: string (default: mp3_standard) - Audio output format: MP3 128/192 kbps or WAV at 16/22/24/44.1 kHz
  Options: mp3_standard, mp3_high_quality, wav_16khz, wav_22khz, wav_24khz, wav_cd_quality

## Examples

### Core.Today company song
The same Korean company-song lyrics given to every music model — compare how each one sings them
```json
{
  "model": "elevenlabs/music",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female and male vocals singing in Korean, catchy chant chorus, synth brass, punchy drums. Lyrics: [Verse] 아침부터 AI, 커피보다 진해 / 코딩하다 보니 벌써 새벽 두 시네! / 안 되는 건 없어, 일단 만들어 봐 / 상상이 현실 되는 마법 같은 회사! [Chorus] 코어! 닷! 투데이! / 오늘의 상상이 내일의 기술로! / 코어! 닷! 투데이! / AI도 놀라는 우리의 아이디어!",
    "music_length_ms": 30000,
    "force_instrumental": false,
    "output_format": "mp3_high_quality"
  }
}
```

### 20-second dance track
Upbeat EDM with a female vocal hook, 192 kbps MP3 — 390 credits
```json
{
  "model": "elevenlabs/music",
  "input": {
    "prompt": "Upbeat electronic dance music with a driving bassline, bright synth leads and an energetic female vocal hook",
    "music_length_ms": 20000,
    "force_instrumental": false,
    "output_format": "mp3_high_quality"
  }
}
```

## 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
- Set music_length_ms to exactly what you need — every second is billed
- force_instrumental defaults to true; set it to false when you want vocals
- Use mp3_standard for previews and wav_cd_quality for masters
- For 1-minute-plus songs compare with the fal.ai version (elevenlabs/music/v2.5), billed per started minute