> ## Documentation Index
> Fetch the complete documentation index at: https://docs.varg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Music Generation

> AI music generation for video soundtracks, background music, and jingles

## Overview

Generate music from text descriptions. Currently one model is available via ElevenLabs.

| Model ID   | Credits | \~Cost |
| ---------- | ------- | ------ |
| `music_v1` | 30      | \$0.30 |

## Quick start

<CodeGroup>
  ```typescript SDK theme={null}
  import { createVarg } from "vargai/ai"

  const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

  const result = await varg.musicModel().generate({
    prompt: "upbeat electronic music, cheerful vibes, 120 bpm",
    duration: 15,
  })

  console.log(result.audio.url)
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v2/music \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "music_v1",
      "prompt": "upbeat electronic music, cheerful vibes, 120 bpm",
      "duration": 15
    }'
  ```
</CodeGroup>

## Parameters

<ResponseField name="prompt" type="string" required>
  Text description of the music. Include genre, mood, tempo, and instruments for best results.
</ResponseField>

<ResponseField name="duration" type="number">
  Music duration in seconds. **Always set this explicitly** — without it, the model defaults to \~60 seconds which may be more than needed.
</ResponseField>

<Warning>
  **Always set `duration` explicitly.** Without it, the model generates \~60 seconds of music, which costs the same but may be more than you need.
</Warning>

## Prompt examples

| Prompt                                             | Good for                  |
| -------------------------------------------------- | ------------------------- |
| `"chill lofi hip hop, relaxing study vibes"`       | Background music, ambient |
| `"epic orchestral cinematic trailer music"`        | Product launches, drama   |
| `"upbeat pop, energetic, catchy melody"`           | Social media, TikTok      |
| `"acoustic guitar, gentle fingerpicking, warm"`    | Narration background      |
| `"dark ambient electronic, mysterious atmosphere"` | Thriller/tech content     |
| `"jazz piano trio, smooth and sophisticated"`      | Interviews, podcasts      |

## Composition example

Add music as a background track in a video:

```tsx theme={null}
<Render width={1080} height={1920} fps={30}>
  <Music
    prompt="upbeat electronic music, cheerful vibes"
    model={varg.musicModel()}
    volume={0.3}
    duration={15}
  />
  <Clip duration={5}>
    <Video model={varg.videoModel("kling-v3")} prompt="sunset timelapse" duration={5} />
  </Clip>
  <Clip duration={10}>
    <Video model={varg.videoModel("kling-v3")} prompt="city nightscape" duration={10} />
  </Clip>
</Render>
```

## Pricing

| Model      | Credits | USD    |
| ---------- | ------- | ------ |
| `music_v1` | 30      | \$0.30 |

## Tips

* **Include genre, mood, tempo, and instruments** in your prompt for the best results.
* **BPM matters** — specify it if you need the music to match a specific pacing (e.g., `"120 bpm"` for upbeat, `"70 bpm"` for relaxed).
* **Set volume to 0.2-0.4** when using as background under narration — it shouldn't compete with speech.

## Related models

<CardGroup cols={2}>
  <Card title="ElevenLabs Speech" icon="microphone" href="/models/speech/elevenlabs">
    Add narration over your music track.
  </Card>
</CardGroup>