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

# MiniMax Music 2.6 · Text to music

> Generate songs with custom or automatic lyrics, or vocal-free instrumental tracks. Track length is model-determined.

[← MiniMax Music](/api-documentation/ai-generation/models/minimax-music)

**Model name:** `minimax-music-2.6/text-to-music`\
**Generation type:** `text_to_music`\
**Endpoint:** [`POST /api/asset_generator/`](/api-reference/ai-generation/post-ai-generation)

## Pricing

**3.0** credits per output.

Prices are per output. When a request asks for several outputs, the charge is this price times the number of outputs.

## Quick start

<CodeGroup>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.creatify.ai/api/asset_generator/ \
    --header 'Content-Type: application/json' \
    --header 'X-API-ID: your-api-id' \
    --header 'X-API-KEY: your-api-key' \
    --data '{
      "model_name": "minimax-music-2.6/text-to-music",
      "input_params": {
        "prompt": "An upbeat acoustic track for a summer product ad.",
        "model": "music-2.6",
        "audio_setting": {
          "sample_rate": 44100,
          "bitrate": 128000,
          "format": "mp3"
        },
        "output_format": "url"
      }
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://api.creatify.ai/api/asset_generator/",
      headers={"X-API-ID": "your-api-id", "X-API-KEY": "your-api-key"},
      json={
          "model_name": "minimax-music-2.6/text-to-music",
          "input_params": {
              "prompt": "An upbeat acoustic track for a summer product ad.",
              "model": "music-2.6",
              "audio_setting": {
                  "sample_rate": 44100,
                  "bitrate": 128000,
                  "format": "mp3"
              },
              "output_format": "url"
          },
      },
  )
  print(response.json()["id"])
  ```
</CodeGroup>

## Input parameters

Send these fields in `input_params`.

<ParamField body="prompt" type="string" required>
  The text description that guides the audio generation process. This prompt defines what you want to hear in the generated audio content.

  Minimum characters: `1`.
  Maximum characters: `2000`.
</ParamField>

<ParamField body="model" type="string" required default={"music-2.6"}>
  The AI model to use for music generation

  Allowed values: `"music-2.6"`.
</ParamField>

<ParamField body="audio_setting" type="object" required>
  Audio configuration settings
</ParamField>

<ParamField body="output_format" type="string" required default={"url"}>
  Specifies the format of the output audio.

  Allowed values: `"url"`.
</ParamField>

<ParamField body="lyrics" type="string">
  Optional lyrics with structure tags such as \[Verse] and \[Chorus]. Leave empty to generate lyrics from the prompt.

  Minimum characters: `0`.
  Maximum characters: `3500`.
</ParamField>

<ParamField body="lyrics_optimizer" type="boolean" default={true}>
  Generate lyrics from the prompt when lyrics are empty.
</ParamField>

<ParamField body="is_instrumental" type="boolean" default={false}>
  Generate music without vocals; lyrics are not required.
</ParamField>

<Accordion title="Complete JSON schema">
  ```json theme={null}
  {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "prompt",
      "model",
      "audio_setting",
      "output_format"
    ],
    "properties": {
      "model": {
        "enum": [
          "music-2.6"
        ],
        "type": "string",
        "title": "Model",
        "default": "music-2.6",
        "description": "The AI model to use for music generation",
        "x-is-hidden": true
      },
      "lyrics": {
        "type": "string",
        "title": "Lyrics",
        "maxLength": 3500,
        "minLength": 0,
        "description": "Optional lyrics with structure tags such as [Verse] and [Chorus]. Leave empty to generate lyrics from the prompt."
      },
      "prompt": {
        "type": "string",
        "title": "Prompt",
        "maxLength": 2000,
        "minLength": 1,
        "description": "The text description that guides the audio generation process. This prompt defines what you want to hear in the generated audio content.",
        "x-ui-name": "prompt"
      },
      "audio_setting": {
        "type": "object",
        "title": "Audio Settings",
        "required": [
          "sample_rate",
          "bitrate",
          "format"
        ],
        "x-ui-name": "audioSettings",
        "properties": {
          "format": {
            "enum": [
              "mp3"
            ],
            "type": "string",
            "title": "Format",
            "default": "mp3",
            "description": "Audio format",
            "x-is-hidden": true
          },
          "bitrate": {
            "enum": [
              64000,
              128000,
              256000
            ],
            "type": "integer",
            "title": "Bitrate",
            "default": 128000,
            "description": "The bitrate of the generated audio in kbps (kilobits per second). Higher bitrates preserve more audio quality but create larger files.",
            "x-advance-settings": true
          },
          "sample_rate": {
            "enum": [
              24000,
              32000,
              44100
            ],
            "type": "integer",
            "title": "SampleRate",
            "default": 44100,
            "x-ui-name": "sampleRate",
            "description": "The sample rate of the generated audio in Hz (samples per second). Higher sample rates capture more audio detail and frequency range but result in larger file sizes.",
            "x-advance-settings": true
          }
        },
        "description": "Audio configuration settings"
      },
      "output_format": {
        "enum": [
          "url"
        ],
        "type": "string",
        "title": "Output format",
        "default": "url",
        "x-ui-name": "outputFormat",
        "description": "Specifies the format of the output audio.",
        "x-is-hidden": true
      },
      "lyrics_optimizer": {
        "type": "boolean",
        "title": "Auto-generate lyrics",
        "default": true,
        "description": "Generate lyrics from the prompt when lyrics are empty.",
        "x-advance-settings": true
      },
      "is_instrumental": {
        "type": "boolean",
        "title": "Instrumental only",
        "default": false,
        "description": "Generate music without vocals; lyrics are not required."
      }
    },
    "allOf": [
      {
        "if": {
          "properties": {
            "is_instrumental": {
              "const": false
            },
            "lyrics_optimizer": {
              "const": false
            }
          },
          "required": [
            "is_instrumental",
            "lyrics_optimizer"
          ]
        },
        "then": {
          "required": [
            "lyrics"
          ],
          "properties": {
            "lyrics": {
              "minLength": 1
            }
          }
        }
      }
    ]
  }
  ```
</Accordion>

## Response

The request returns the task with `status: "initializing"`. Poll [GET /api/asset\_generator/\{id}/](/api-reference/ai-generation/get-ai-generation-) until `status` is `done` or `failed`, or pass a `webhook_url` to be notified. A finished task lists its files in `assets` and the credits it charged in `credits_used`.


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