## Basic model info

- Model name: minimax/minimax minimax-music3
- Model description: MiniMax Music 3.0 generates a complete, production-ready song — composition, arrangement, vocals and mixing — from a style prompt and lyrics in a single pass. It holds musical theme, rhythm, vocal identity and arrangement progression across full song structures (intro, verse, pre-chorus, chorus, bridge, instrumental break, outro) for tracks up to five minutes. Supports instrumental-only output and automatic lyric writing.
- Endpoint name: text-to-music


## Model schema

The model schema is defined in the OpenAPI schema: [OpenAPI Schema](https://oapi.sunra.ai/main/minimax/minimax-music3/latest.json)

### Model input schema

The model input schema is:



```json
{
  "description": "Input schema for MiniMax Music 3.0 song generation.",
  "properties": {
    "prompt": {
      "description": "Description of the music to generate: style, mood, instrumentation, tempo and vocal characteristics.",
      "maxLength": 2000,
      "title": "Prompt",
      "type": "string",
      "x-sr-order": 200
    },
    "bitrate": {
      "default": 256000,
      "description": "Bitrate of the generated audio, in bits per second.",
      "enum": [
        32000,
        64000,
        128000,
        256000
      ],
      "title": "Bitrate",
      "type": "integer",
      "x-sr-order": 402
    },
    "is_instrumental": {
      "default": false,
      "description": "Generate an instrumental track with no vocals.",
      "title": "Is Instrumental",
      "type": "boolean",
      "x-sr-order": 501
    },
    "lyrics": {
      "anyOf": [
        {
          "maxLength": 3500,
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "description": "Lyrics of the song, with lines separated by newlines and optional structure tags such as [intro], [verse], [chorus], [bridge] and [outro]. Required unless lyrics_optimizer or is_instrumental is enabled.",
      "title": "Lyrics",
      "x-sr-order": 201
    },
    "lyrics_optimizer": {
      "default": false,
      "description": "Write the lyrics automatically from the prompt instead of requiring the lyrics field.",
      "title": "Lyrics Optimizer",
      "type": "boolean",
      "x-sr-order": 500
    },
    "output_audio_format": {
      "default": "mp3",
      "description": "Container format of the generated audio.",
      "enum": [
        "mp3",
        "wav",
        "pcm"
      ],
      "title": "Output Audio Format",
      "type": "string",
      "x-sr-order": 400
    },
    "sample_rate": {
      "default": 44100,
      "description": "Sample rate of the generated audio, in Hz.",
      "enum": [
        16000,
        24000,
        32000,
        44100
      ],
      "title": "Sample Rate",
      "type": "integer",
      "x-sr-order": 401
    }
  },
  "required": [
    "prompt"
  ],
  "title": "TextToMusicInput",
  "type": "object"
}
```



### Model output schema

The model output schema is:



```json
{
  "description": "Output schema for MiniMax Music 3.0 song generation.",
  "properties": {
    "audio": {
      "properties": {
        "content_type": {
          "description": "The mime type of the file.",
          "title": "Content Type",
          "type": "string"
        },
        "file_name": {
          "description": "The name of the file. It will be auto-generated if not provided.",
          "title": "File Name",
          "type": "string"
        },
        "file_size": {
          "description": "The size of the file in bytes.",
          "title": "File Size",
          "type": "integer"
        },
        "url": {
          "description": "The URL where the file can be downloaded from.",
          "title": "Url",
          "type": "string"
        }
      },
      "required": [
        "content_type",
        "file_name",
        "file_size",
        "url"
      ],
      "title": "SunraFile",
      "type": "object"
    },
    "output_audio_duration": {
      "title": "Output Audio Duration",
      "type": "integer"
    }
  },
  "required": [
    "audio",
    "output_audio_duration"
  ],
  "title": "MusicOutput",
  "type": "object"
}
```



## Example inputs and outputs

Use the following example inputs and outputs to understand the model.

### Input example



```json
{
  "prompt": "",
  "bitrate": 256000,
  "is_instrumental": false,
  "lyrics": null,
  "lyrics_optimizer": false,
  "output_audio_format": "mp3",
  "sample_rate": 44100
}
```



### Output example



```json
{
}
```



## Model code examples

### JavaScript



```javascript
import { sunra } from "@sunra/client";

const result = await sunra.subscribe("minimax/minimax-music3/text-to-music", {
  input: {
  	prompt: '',
  	lyrics: null,
  	output_audio_format: 'mp3',
  	sample_rate: 44100,
  	bitrate: 256000,
  	lyrics_optimizer: false,
  	is_instrumental: false
  },
  logs: true,
  onQueueUpdate: (update) => {
    console.log(`Status Update: ${update.status}, Request ID: ${update.request_id}`);
  },
});
console.log(result.data);
console.log(result.requestId);
```



### Python



```python
import sunra_client

result = sunra_client.subscribe(
    "minimax/minimax-music3/text-to-music",
    arguments={
        "prompt": "",
        "lyrics": None,
        "output_audio_format": "mp3",
        "sample_rate": 44100,
        "bitrate": 256000,
        "lyrics_optimizer": False,
        "is_instrumental": False
    },

    with_logs=True,
    on_enqueue=print,
    on_queue_update=print,
)
print(result)
```



### Java



```java
import ai.sunra.client.*;
import java.util.Map;
import com.google.gson.JsonObject;

var client = SunraClient.withEnvCredentials();

var response = client.subscribe(
    "minimax/minimax-music3/text-to-music",
    SubscribeOptions.<JsonObject>builder()
        .input(Map.of(
            "prompt", "",
            "lyrics", null,
            "output_audio_format", "mp3",
            "sample_rate", 44100,
            "bitrate", 256000,
            "lyrics_optimizer", false,
            "is_instrumental", false))

        .resultType(JsonObject.class)
        .onQueueUpdate(update -> System.out.printf(
            "\nStatus Update: %s, Request ID: %s%n",
            update.getStatus(),
            update.getRequestId()
        ))
        .logs(true)
        .build()
);

System.out.println("Completed!");
System.out.println(response.getData());
  
```



### Kotlin



```kotlin
import ai.sunra.client.kt.*
import com.google.gson.JsonObject

val client = createSunraClient()

val response = client.subscribe<JsonObject>(
    endpointId = "minimax/minimax-music3/text-to-music",
    input = mapOf(
            "prompt" to "",
            "lyrics" to null,
            "output_audio_format" to "mp3",
            "sample_rate" to 44100,
            "bitrate" to 256000,
            "lyrics_optimizer" to false,
            "is_instrumental" to false),
    options = ai.sunra.client.kt.SubscribeOptions(logs = true),
    onUpdate = { update ->
        println("\nStatus Update: ${update.status}, Request ID: ${update.requestId}")
    }
)

println("Completed!")
println(response.data)
  
```



### Curl



```bash

curl --request POST \
  --url https://api.sunra.ai/v1/queue/minimax/minimax-music3/text-to-music \
  --header "Authorization: Key $SUNRA_KEY" \
  --header "Content-Type: application/json" \
  --data '{"prompt":"","lyrics":null,"output_audio_format":"mp3","sample_rate":44100,"bitrate":256000,"lyrics_optimizer":false,"is_instrumental":false}'
    
```



## Model readme

>