# Mureka Song - Core.Today AI API

> Mureka song generation via fal.ai. Two modes: lyrics-to-song (send your lyrics, the prompt steers the style) or prompt-to-song (prompt plus genre styles, the model writes the lyrics). Choose the Mureka model version. Returns an MP3 with timed lyric sections.

- **Provider**: Mureka
- **Model ID**: mureka/api/generate/song
- **Category**: Audio & TTS
- **Credits**: 1740 per prompt-to-song with mureka-9.5 (1740); other versions 1050. Lyrics-to-song: mureka-9.5 520, mureka-9/8/o2 160, mureka-7.6 100
- **Speed**: Medium
- **Quality**: High

## Features
- Lyrics-to-song and prompt-to-song modes
- Five model versions from mureka-7.6 to mureka-9.5
- Genre styles (pop, rock, jazz, k-pop, lo-fi, ...) for prompt-to-song
- Vocal gender preference for lyrics-to-song
- Returns timed lyric sections with the audio

## Use Cases
- Turning written lyrics into a finished song
- Fast genre-tagged songs from a one-line idea
- K-pop / J-pop style demos

## 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 - Describe the desired song, mood, instrumentation, and vocals. With lyrics it acts as a style control

### Optional
- **lyrics**: string - Lyrics to sing, up to 5,000 characters. Provide for lyrics-to-song (cheaper); omit for prompt-to-song
- **model**: string (default: mureka-9.5) - The Mureka model version to use
  Options: mureka-9.5, mureka-9, mureka-8, mureka-o2, mureka-7.6
- **gender**: string - Preferred vocal gender for lyrics-to-song generation
  Options: female, male
- **styles**: array - One or more genres for prompt-to-song (pop, rock, jazz, r&b, edm, ambient, folk, latin, k-pop, j-pop, house, gospel, lo-fi). Cannot be combined with lyrics

## Examples

### Core.Today company song
The same Korean company-song lyrics given to every music model — compare how each one sings them
```json
{
  "model": "mureka/api/generate/song",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female vocals, catchy chant chorus, synth brass, punchy drums, fun and playful",
    "lyrics": "[verse]\n아침부터 AI, 커피보다 진해\n코딩하다 보니 벌써 새벽 두 시네!\n안 되는 건 없어, 일단 만들어 봐\n상상이 현실 되는 마법 같은 회사!\n\n[chorus]\n코어! 닷! 투데이!\n오늘의 상상이 내일의 기술로!\n코어! 닷! 투데이!\nAI도 놀라는 우리의 아이디어!\n\n[outro]\n뚝딱뚝딱 만들고, 반짝반짝 빛내고!\n기술을 넘어 경험으로!\n코어닷투데이, Hey!",
    "model": "mureka-9.5",
    "gender": "female"
  }
}
```

### Prompt-to-song with styles
One-line idea plus genres; the model writes the lyrics
```json
{
  "model": "mureka/api/generate/song",
  "input": {
    "prompt": "A bright summer love song with a catchy chorus",
    "model": "mureka-9.5",
    "styles": [
      "pop",
      "rock"
    ]
  }
}
```

### Lyrics-to-song
Your own lyrics with a style prompt and vocal gender — a third of the price
```json
{
  "model": "mureka/api/generate/song",
  "input": {
    "prompt": "Warm acoustic ballad, slow tempo, soft piano and strings",
    "lyrics": "[verse]\n창가에 남은 빛이 너를 닮아\n조용히 번지는 저녁\n\n[chorus]\n다시 부르면 돌아올까\n그날의 우리",
    "model": "mureka-9.5",
    "gender": "female"
  }
}
```

## 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
- Send lyrics whenever you have them — lyrics-to-song is about a third of the prompt-to-song price
- styles only applies to prompt-to-song and is rejected together with lyrics
- mureka-9.5 is the best quality; mureka-7.6 is the cheapest for drafts
- The response includes timed lyric sections — useful for subtitles and lyric videos