# ElevenLabs Music v2.5 - Core.Today AI API

> ElevenLabs Music v2.5 via fal.ai. Composes a song from a text prompt with a target length of 3 seconds to 10 minutes, optional vocals, and MP3 / Opus output. Billed per output minute, rounded up — the best value for songs of one minute or more.

- **Provider**: ElevenLabs
- **Model ID**: elevenlabs/music/v2.5
- **Category**: Audio & TTS
- **Credits**: 1400 per minute of music_length_ms, rounded up
- **Speed**: Medium
- **Quality**: High

## Features
- 3 seconds to 10 minutes per song
- Per-minute billing (rounded up to the next minute)
- Vocals or forced instrumental
- MP3 up to 320 kbps or Opus output

## Use Cases
- Full-length songs of one minute or more
- Long background music up to 10 minutes
- Vocal tracks for video and ads

## 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 text prompt describing the music to generate (genre, mood, instruments, tempo, vocals)

### Optional
- **music_length_ms**: integer (default: 60000) - Length in milliseconds (3,000-600,000). Billed per started minute; 60,000 is sent when omitted
- **force_instrumental**: boolean (default: false) - If true, guarantees an instrumental song; if false the model decides from the prompt
- **output_format**: string (default: mp3_48000_192) - Output format as codec_samplerate_bitrate, e.g. mp3_44100_128
  Options: mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, mp3_48000_128, mp3_48000_192, mp3_48000_240, mp3_48000_320, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192

## 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/v2.5",
  "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! [Outro] 뚝딱뚝딱 만들고, 반짝반짝 빛내고! / 기술을 넘어 경험으로! / 코어닷투데이, Hey!",
    "music_length_ms": 60000,
    "force_instrumental": false,
    "output_format": "mp3_48000_192"
  }
}
```

### One-minute soundtrack
Cinematic jungle theme with tribal percussion
```json
{
  "model": "elevenlabs/music/v2.5",
  "input": {
    "prompt": "Mysterious original soundtrack, themes of jungle, rainforest, nature, woodwinds, busy rhythmic tribal percussion.",
    "music_length_ms": 60000,
    "output_format": "mp3_48000_192"
  }
}
```

## 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
- Request lengths in whole minutes (60,000 / 120,000 ms) — 61 seconds costs the same as 2 minutes
- For clips shorter than a minute use elevenlabs/music on Replicate (per-second billing)
- Describe vocals explicitly ('female lead vocal singing ...') or set force_instrumental
- mp3_48000_192 is the default; mp3_48000_320 for masters, opus_* for streaming