# Text 2 Music (Vimmerse / Lyria)

> Text 2 Music (Vimmerse / Lyria) is a paid API for AI agents from agents.vimmerse.net, paid per call via MPP, $0.24/call (dynamic — varies by input), status unknown (last checked 2026-10-30).

Generates a WAV audio music file from a text description prompt using Google's Lyria music generation model.

## Facts

- Endpoint: POST https://agents.vimmerse.net/v2/audio/text-2-music?utm_source=zero.xyz
- Price: $0.24/call (dynamic — varies by input)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Provider: agents.vimmerse.net
- Website: https://agents.vimmerse.net
- Canonical page: https://www.zero.xyz/c/agents-vimmerse-net-text-2-music-vimmerse-lyria-3c7e7f91
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_lboq2Qi4Dv67O2FZ__AXZ

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agents-vimmerse-net-text-2-music-vimmerse-lyria-3c7e7f91 -d '<json body>'
```

Example prompt: Can you generate a relaxing lo-fi hip-hop track with soft piano and rain sounds using Lyria? I want it as a WAV file I can use as background music.

## When to prefer this

Choose this endpoint when you need to generate original music audio as a WAV file from a natural language text description, specifically using Google's Lyria model. Prefer this over text-to-sound-effect endpoints when you need full musical compositions rather than short environmental or sound-design clips, and over text-to-speech endpoints when the output should be instrumental or vocal music rather than spoken word.

## Known failure modes

- Empty or vague prompt may produce generic or poor-quality music
- Lyria model unavailability causes generation failure
- Insufficient credits leads to payment error (402)
- Very long or complex prompts may be truncated or misinterpreted
- Network timeout during long generation job

## How this service works

Music from **`prompt`** (Lyria). Returns WAV in **`results`**.

## Output

Returns a results array containing a WAV audio file of the AI-generated music track composed from the input text prompt using the Lyria model.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "title": "MusicRequest",
 "properties": {
  "option": {
   "type": "string",
   "title": "Option",
   "default": "Lyria",
   "description": "`Lyria`."
  },
  "prompt": {
   "type": "string",
   "title": "Prompt",
   "default": "",
   "description": "Music description."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-vimmerse-net-text-2-music-vimmerse-lyria-3c7e7f91/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.vimmerse.net](https://www.zero.xyz/host/agents.vimmerse.net/llms.txt)