Turn Lyrics into Songs · MiniMax

Turn your lyrics or a music idea into a song, or make instrumental music without singing. Describe the style or mood, then save the audio before the download link expires.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Create audio from the user’s request. If the user wants singing and provides lyrics, use those words as the starting lyrics, but do not promise every word will be sung exactly. Write new lyrics only when asked, using the user’s idea; for instrumental music, do not ask for lyrics. Ask a short follow-up if the user has not made clear whether they want singing or instrumental music. Choose a commonly playable audio file unless the user asks for another supported choice. Check the current price and use only the budget the user approved. Return the actual audio link and remind the user to save the file within 24 hours. Encourage listening before relying on exact words or sound quality. Do not claim a specific singer, exact song length, quality score, or usage rights.

Task:
Create [a song with singing or music without singing] about [topic or feeling]. If I provide [lyrics], use them; if I ask for new lyrics, write them based on [my idea]. If I have a preference, use [music style or mood]. Remind me to download and save the music within 24 hours.

Paste into your connected AI's conversation.

Connection guide

Up to 0.18 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

MiniMax

Turn Lyrics into Songs · MiniMax

Turn your lyrics or a music idea into a song, or make instrumental music without singing. Describe the style or mood, then save the audio before the download link expires.

You receive

Create a song from lyrics or an idea, or make an instrumental track without singing. Receive a link to the finished audio so you can listen and save it.

Start with your task

Create [a song with singing or music without singing] about [topic or feeling]. If I provide [lyrics], use them; if I ask for new lyrics, write them based on [my idea]. If I have a preference, use [music style or mood]. Remind me to download and save the music within 24 hours.

What to know

The download link expires after 24 hours. A sung song may not follow every lyric or musical detail exactly. This Tool does not promise a particular singer or exact song length.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Music request settings`body`	`object`	Optional	Usable music request: provide lyrics for a song, or the documented prompt/flag combination for instrumental or automatic lyrics. The root and body have no formal required list; the mode conditions still govern the intended task.
Music model`body.model`	`string`	Optional	Generation-model selector: music-3.0 or music-2.6, default music-3.0. Default `music-3.0` Options `music-3.0, music-2.6`
Song lyrics`body.lyrics`	`string`	Optional	Nonempty supplied lyrics, 1–3500 characters, with line breaks and supported section tags such as [Verse]/[Chorus]. Needed unless instrumental or automatic-lyrics mode applies; omit absent lyrics, never send an empty string. Minimum length `1` Maximum length `3500`
Music description or lyric idea`body.prompt`	`string`	Optional	Music style, mood and scenario text, at most 2000 characters. A meaningful prompt is required for instrumental music and supplies the lyric idea when lyrics_optimizer is true with lyrics omitted. Maximum length `2000`
Non-streaming generation`body.stream`	`boolean`	Optional	Fixed false: generate and return music as a non-streaming result. Default `false` Fixed value `false`
Audio output settings`body.audio_setting`	`object`	Optional	Object selecting requested audio format, sampling frequency and encoding data rate. These settings describe audio delivery rather than song tempo.
Requested audio format`body.audio_setting.format`	`string`	Optional	Audio representation choice: mp3, wav or pcm. Handle the actual delivered file in its returned format. Options `mp3, wav, pcm`
Requested encoding rate`body.audio_setting.bitrate`	`number`	Optional	Requested audio encoding data rate: 32000, 64000, 128000 or 256000. This controls the encoding setting rather than the musical tempo.
Requested sampling rate`body.audio_setting.sample_rate`	`number`	Optional	Requested audio sampling frequency: 16000, 24000, 32000 or 44100. Select one declared value; sampling frequency is separate from song tempo and duration.
Temporary audio link output`body.output_format`	`string`	Optional	Fixed url, returning an audio retrieval link documented to expire after 24 hours. Save the generated file while the link is available. Default `url` Fixed value `url`
Request instrumental music`body.is_instrumental`	`boolean`	Optional	Boolean, default false, requesting instrumental music without vocals. When true, provide a nonempty prompt; lyrics are not required. Default `false`
Generate lyrics from an idea`body.lyrics_optimizer`	`boolean`	Optional	Boolean, default false. When true and lyrics are omitted, generate lyrics from prompt. The Tool’s minimum lyric length means omission is the supported representation of absent lyrics. Default `false`

View raw JSON

{
  "type": "object",
  "required": [],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "model": {
          "enum": [
            "music-3.0",
            "music-2.6"
          ],
          "type": "string",
          "default": "music-3.0",
          "description": "Music model. music-3.0 is MiniMax's current recommended generation; music-2.6 is the previous one. Same $0.15 price per song."
        },
        "lyrics": {
          "type": "string",
          "maxLength": 3500,
          "minLength": 1,
          "description": "Song lyrics, using \\n to separate lines. Supports structure tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Bridge], [Outro], [Solo], etc. Required unless is_instrumental or lyrics_optimizer is true."
        },
        "prompt": {
          "type": "string",
          "maxLength": 2000,
          "description": "Description of the music's style, mood, and scenario. Required when is_instrumental is true."
        },
        "stream": {
          "type": "boolean",
          "const": false,
          "default": false,
          "description": "Streaming is not supported; always false. Fixed."
        },
        "audio_setting": {
          "type": "object",
          "properties": {
            "format": {
              "enum": [
                "mp3",
                "wav",
                "pcm"
              ],
              "type": "string",
              "description": "Audio format."
            },
            "bitrate": {
              "anyOf": [
                {
                  "type": "number",
                  "const": 32000
                },
                {
                  "type": "number",
                  "const": 64000
                },
                {
                  "type": "number",
                  "const": 128000
                },
                {
                  "type": "number",
                  "const": 256000
                }
              ],
              "description": "Bitrate."
            },
            "sample_rate": {
              "anyOf": [
                {
                  "type": "number",
                  "const": 16000
                },
                {
                  "type": "number",
                  "const": 24000
                },
                {
                  "type": "number",
                  "const": 32000
                },
                {
                  "type": "number",
                  "const": 44100
                }
              ],
              "description": "Sampling rate."
            }
          },
          "description": "Audio output configuration.",
          "additionalProperties": false
        },
        "output_format": {
          "type": "string",
          "const": "url",
          "default": "url",
          "description": "Audio is always returned as a CDN URL (link EXPIRES after 24h). Fixed — no other value is accepted."
        },
        "is_instrumental": {
          "type": "boolean",
          "default": false,
          "description": "Generate instrumental music (no vocals). When true, prompt is required."
        },
        "lyrics_optimizer": {
          "type": "boolean",
          "default": false,
          "description": "Auto-generate lyrics from the prompt when lyrics is empty."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Create a song from your own lyrics, ask for new lyrics based on an idea, or make instrumental music without singing. If you provide lyrics, keep them under 3,500 characters.

Describe the musical style, mood, or scene in everyday words. For example: [gentle guitar music for a rainy afternoon].

The result is a link to the audio. Listen to check the music and sung words; the finished performance may differ from your request.

The download link expires after 24 hours, so save the audio before then. The generated result may not match every detail of your request.

MiniMax music generation guide

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Provide [your lyrics] for a sung song, or give [a music idea] and ask for new lyrics. For instrumental music, describe [the sound or mood] instead.

Turn Lyrics into Songs · MiniMax

Turn Lyrics into Songs · MiniMax

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose music with or without singing

Describe the style

Listen and save your music

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Choose music with or without singing

Describe the style

Listen and save your music

Questions about this tool.

What can I provide to make music?

Can I use my own lyrics?

How do I make instrumental music?

Can I choose a particular singer or exact length?

How long can I download the audio?

Does a successful result guarantee quality or usage rights?