# Mureka 9 Song Generation

> Generates songs from a text prompt or supplied lyrics, with musical style, vocal, reference-audio, and melody controls, plus support for multiple variations.



## Overview

- **Endpoint**: `https://fal.run/mureka/v9/generate/song`
- **Model ID**: `mureka/v9/generate/song`
- **Category**: text-to-audio
- **Kind**: inference
**Tags**: music, vocals, song generation



## Pricing

Billing is calculated per generated song. When you provide **lyrics**, your request will cost **$0.045** per song; when you provide only a **prompt** without lyrics, it will cost **$0.30** per song. Each request returns one song. For **$1** you can generate about **22 songs** from your own lyrics or **3 songs** from a prompt alone.

For more details, see [fal.ai pricing](https://fal.ai/pricing).

## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:


- **`lyrics`** (`string`, _optional_):
  Lyrics to sing, up to 5,000 characters. Provide this for lyrics-to-song generation; otherwise provide prompt for prompt-to-song generation.

- **`styles`** (`list<Enum>`, _optional_):
  One or more musical genres for prompt-to-song generation. This cannot be used when lyrics is provided.
  - Array of Enum
  - Examples: ["pop","rock"]

- **`prompt`** (`string`, _optional_):
  Describe the desired song, mood, instrumentation, and vocals. Required when lyrics is omitted, up to 2,000 characters. With lyrics, it acts as a music-style control and supports up to 1,024 characters.
  - Examples: "A bright summer love song with a catchy chorus"

- **`gender`** (`Enum`, _optional_):
  Preferred vocal gender for lyrics-to-song generation. An uploaded or cloned voice takes precedence.
  - Options: `"female"`, `"male"`

- **`reference_id`** (`string`, _optional_):
  Reference-music ID returned by /files/upload with purpose='reference'.

- **`vocal_id`** (`string`, _optional_):
  Voice ID returned by /voice/clone.

- **`melody_id`** (`string`, _optional_):
  Melody ID returned by /files/upload with purpose='melody'. This cannot be combined with prompt, reference_id, or vocal_id.

- **`enable_safety_checker`** (`boolean`, _optional_):
  Authorized callers may set false to request relaxed screening. Default value: `true`
  - Default: `true`



**Required Parameters Example**:

```json
{}
```

**Full Example**:

```json
{
  "styles": [
    "pop",
    "rock"
  ],
  "prompt": "A bright summer love song with a catchy chorus",
  "enable_safety_checker": true
}
```


### Output Schema

The API returns the following output format:

- **`song_id`** (`string`, _optional_):
  Reusable identifier for this audio. Pass it to endpoints that accept song_id.

- **`audio`** (`File`, _required_):
  The generated audio file.

- **`duration`** (`integer`, _optional_):
  Duration of the generated audio in milliseconds, when available.

- **`lyrics_sections`** (`list<LyricsSection>`, _optional_):
  Timed lyric sections for the generated audio, when available.
  - Array of LyricsSection



**Example Response**:

```json
{
  "audio": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "lyrics_sections": [
    {
      "lines": [
        {
          "words": [
            {}
          ]
        }
      ]
    }
  ]
}
```


## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://fal.run/mureka/v9/generate/song \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{}'
```

### Python

Ensure you have the Python client installed:

```bash
pip install fal-client
```

Then use the API client to make requests:

```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "mureka/v9/generate/song",
    arguments={},
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

### JavaScript

Ensure you have the JavaScript client installed:

```bash
npm install --save @fal-ai/client
```

Then use the API client to make requests:

```javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("mureka/v9/generate/song", {
  input: {},
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);
```


## Deploy your own model

To run your own weights, a fine-tune or a custom pipeline on the GPUs that serve this API, deploy it on fal Serverless. GPUs from H100 (80GB) to B300 (288GB), billed per second; an H100 is $4.50/h list, as low as $2.49/h. Prices, GPU specs and deploy steps: [fal Serverless](https://fal.ai/serverless.md).

## Additional Resources

### Documentation

- [Model Playground](https://fal.ai/models/mureka/v9/generate/song)
- [API Documentation](https://fal.ai/models/mureka/v9/generate/song/api)
- [OpenAPI Schema](https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=mureka/v9/generate/song)

### fal.ai Platform

- [Platform Documentation](https://fal.ai/docs/documentation)
- [Python Client](https://fal.ai/docs/api-reference/client-libraries/python)
- [JavaScript Client](https://fal.ai/docs/api-reference/client-libraries/javascript)

### Other agent-readable surfaces

This file covers one model. To find anything else:

- [Platform overview](https://fal.ai/llms.txt): Entry points and representative endpoint IDs
- [Documentation index](https://fal.ai/docs/llms.txt): Every documentation page
- [Full documentation text](https://fal.ai/docs/llms-full.txt): The whole documentation inlined
- [Pricing](https://fal.ai/pricing.md): Model API and Serverless GPU prices
- [fal Serverless](https://fal.ai/serverless.md): Deploy your own models: GPU prices, specs and steps
- Any other model: `https://fal.ai/models/<endpoint-id>/llms.txt`