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

# Lyria 3.5

> Google's music model: a full song with vocals from a text prompt, optional lyrics in any language (sings Vietnamese). MP3, up to a couple of minutes; length and structure are steered by the prompt. Flat price per song. Output carries Google's SynthID watermark.

## Overview

Google's music model: a full song with vocals from a text prompt, optional lyrics in any language (sings Vietnamese). MP3, up to a couple of minutes; length and structure are steered by the prompt. Flat price per song. Output carries Google's SynthID watermark.

## Specs

| Field | Value |
| - | - |
| Model ID | `lyria-3.5` |
| Best for | Songs with vocals, multilingual lyrics, jingles, soundtracks |
| Context window | 5,000 |
| Input modalities | Text |
| Output modalities | Audio |
| Speed | Medium |
| Cost band | Balanced |
| Release stage | Stable |

## Pricing

| | Price |
| - | :-: |
| Per song | \$0.108 |

Billed per generated song. Every request reports its exact cost in `usage.cost`; the full media price list is on [Pricing](/pricing).

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

# Music is POST /v1/audio/music — see the API reference for the request fields.
response = client.post(
    "/audio/music",
    body={"model": "lyria-3.5", "prompt": "..."},
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=generate-speech&quality_tier=frontier-open"
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.