# Lyria 3 - Core.Today AI API

> Google's Lyria 3 music generation model. Generates 30-second music clips with vocals, lyrics and multi-language support from a text prompt, optionally inspired by up to 10 reference images. Returns an MP3 file.

- **Provider**: Google
- **Model ID**: google/lyria-3
- **Category**: Audio & TTS
- **Credits**: 93 per 30s clip
- **Speed**: Fast
- **Quality**: High

## Features
- 30-second music clips with vocals and lyrics
- Multi-language vocals
- Up to 10 reference images as mood inspiration
- Flat 93 credits per clip — Lyria's entry tier

## Use Cases
- Short-form video and ad background music
- Jingles, intros and stingers
- Quick style exploration before a full-length song

## 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 - Text prompt describing the music to generate. Be specific about genre, instruments, mood, tempo, and style. Include lyrics and vocal style for sung tracks.

### Optional
- **images**: array (default: []) - Input images to inspire the music composition (up to 10 images)
- **seed**: integer - Random seed for more reproducible results (exact determinism not guaranteed)

## Examples

### Core.Today company song
The same Korean company-song lyrics given to every music model — compare how each one sings them
```json
{
  "model": "google/lyria-3",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female vocals singing in Korean, catchy chant chorus, synth brass, punchy drums. Lyrics: 코어! 닷! 투데이! 오늘의 상상이 내일의 기술로! 코어! 닷! 투데이! AI도 놀라는 우리의 아이디어!"
  }
}
```

### Acoustic folk instrumental
A calm instrumental clip from a short style description
```json
{
  "model": "google/lyria-3",
  "input": {
    "prompt": "A calm acoustic folk song with gentle fingerpicked guitar and soft strings, warm and intimate, 90 BPM. Instrumental only."
  }
}
```

### Sung hook with lyrics
Include lyrics and vocal style in the prompt for a sung clip
```json
{
  "model": "google/lyria-3",
  "input": {
    "prompt": "Upbeat synth-pop, 120 BPM, bright female vocals singing 'We light up the night' as the chorus hook, punchy drums and shimmering synths."
  }
}
```

## 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
- Clips are fixed at about 30 seconds — use Lyria 3 Pro or Lyria 3.5 for full-length songs
- Name the genre, tempo (BPM), instruments and vocal style explicitly; vague prompts give generic results
- Write 'Instrumental only' to avoid vocals
- Reference images steer mood and theme, not melody — they also disable the fal fallback route