MiniMax Music 2.6

Music Generation • MiniMax

MiniMax's music generation model that creates full-length songs with vocals from text prompts and lyrics, or instrumental tracks. Supports BPM/key control and auto-generated lyrics.

Model Info
Terms and License	link ↗
More information	link ↗
Pricing	View pricing in the Cloudflare dashboard ↗

const response = await env.AI.run(
  'minimax/music-2.6',
  {
    prompt: 'An upbeat electronic dance track with a catchy synth melody and driving beat',
    is_instrumental: false,
    lyrics_optimizer: true,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "An upbeat electronic dance track with a catchy synth melody and driving beat",
    "is_instrumental": false,
    "lyrics_optimizer": true
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://minimax-algeng-chat-tts-us.oss-us-east-1.aliyuncs.com/music%2Fprod%2Ftts-20260417092034-QxSPMzdbiRxBSbDb.mp3"
  },
  "state": "Completed"
}

Examples

With Lyrics — Generate a song with custom lyrics

TypeScript
cURL

const response = await env.AI.run(
  'minimax/music-2.6',
  {
    prompt: 'A warm acoustic folk ballad with fingerpicked guitar and gentle vocals',
    is_instrumental: false,
    lyrics:
      'Walking down a dusty road\nWith the sunset painting gold\nEvery step a story told\nOf the places I call home',
    lyrics_optimizer: false,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "A warm acoustic folk ballad with fingerpicked guitar and gentle vocals",
    "is_instrumental": false,
    "lyrics": "Walking down a dusty road\nWith the sunset painting gold\nEvery step a story told\nOf the places I call home",
    "lyrics_optimizer": false
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://minimax-algeng-chat-tts-us.oss-us-east-1.aliyuncs.com/music%2Fprod%2Ftts-20260417091919-YiIxwmvIqXtREDcu.mp3"
  },
  "state": "Completed"
}

Instrumental — Generate instrumental music without vocals

TypeScript
cURL

const response = await env.AI.run(
  'minimax/music-2.6',
  {
    prompt: 'A calm lo-fi hip hop instrumental with vinyl crackle and mellow piano chords',
    is_instrumental: true,
    lyrics_optimizer: false,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "A calm lo-fi hip hop instrumental with vinyl crackle and mellow piano chords",
    "is_instrumental": true,
    "lyrics_optimizer": false
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://minimax-algeng-chat-tts-us.oss-us-east-1.aliyuncs.com/music%2Fprod%2Ftts-20260417092057-LOwvBOOdyGvAyHkQ.mp3"
  },
  "state": "Completed"
}

High Quality Audio — Specify audio format and sample rate

TypeScript
cURL

const response = await env.AI.run(
  'minimax/music-2.6',
  {
    prompt: 'An orchestral cinematic score building to an epic crescendo with full symphony',
    format: 'wav',
    is_instrumental: false,
    lyrics_optimizer: true,
    sample_rate: 44100,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "An orchestral cinematic score building to an epic crescendo with full symphony",
    "format": "wav",
    "is_instrumental": false,
    "lyrics_optimizer": true,
    "sample_rate": 44100
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://minimax-algeng-chat-tts-us.oss-us-east-1.aliyuncs.com/music%2Fprod%2Ftts-20260417092208-UGTfqDggHaemCDAW.wav"
  },
  "state": "Completed"
}

Auto-Generated Lyrics — Let the model generate lyrics from the prompt

TypeScript
cURL

const response = await env.AI.run(
  'minimax/music-2.6',
  {
    prompt: 'A cheerful pop song about a summer road trip with friends',
    is_instrumental: false,
    lyrics_optimizer: true,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "minimax/music-2.6",
  "input": {
    "prompt": "A cheerful pop song about a summer road trip with friends",
    "is_instrumental": false,
    "lyrics_optimizer": true
  }
}'

Output
Raw response

{
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "result": {
    "audio": "https://minimax-algeng-chat-tts-us.oss-us-east-1.aliyuncs.com/music%2Fprod%2Ftts-20260417092245-UlqOBbhqSXtRPopt.mp3"
  },
  "state": "Completed"
}

Parameters

Input
Output

▶bitrate

one of

format

stringenum: mp3, wavAudio format

is_instrumental

booleanrequireddefault: falseGenerate instrumental music (no vocals)

lyrics

stringmaxLength: 3500minLength: 1Song lyrics, using \n to separate lines

lyrics_optimizer

booleanrequireddefault: falseAutomatically generate lyrics based on the prompt description

prompt

stringrequiredmaxLength: 2000Description of the music style, mood, and scenario

▶sample_rate

one of

audio

stringformat: uriURL to the generated audio file

API Schemas (Raw)

Input

Output