MODEL ID minimax:music@2.6

api-only

MiniMax Music 2.6

by MiniMax April 10, 2026

MiniMax Music 2.6 is MiniMax’s latest music generation model for full vocal songs and instrumentals from text prompts. It supports natural-language prompts or detailed production-style instructions, follows specified BPM and key with high reliability, and exposes fine-grained song structure control through section tags. The same Music API also supports instrumental generation, lyrics-assisted workflows, and synchronous or streaming delivery.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat string default: MP3

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP3`: Compressed audio, smaller file size.
`WAV`: Uncompressed, high-quality audio.
`FLAC`: Lossless compression.
`OGG`: Open-source compressed audio format (Vorbis codec).

Allowed values 4 values

audioSettings object

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (MP3 and OGG). When using lossless formats (WAV or FLAC), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For OGG, bitrate limits also vary by the number of channels.

MP3 bitrate limits

Bitrate limits for MP3 are the same regardless of mono or stereo.

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	64 kbps
11,025 Hz	8 kbps	64 kbps
12,000 Hz	8 kbps	64 kbps
16,000 Hz	8 kbps	160 kbps
22,050 Hz	8 kbps	160 kbps
24,000 Hz	8 kbps	160 kbps
32,000 Hz	32 kbps	320 kbps
44,100 Hz	32 kbps	320 kbps
48,000 Hz	32 kbps	320 kbps

OGG bitrate limits — Mono (1 channel)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	40 kbps
12,000 Hz	16 kbps	48 kbps
16,000 Hz	16 kbps	96 kbps
24,000 Hz	16 kbps	80 kbps
48,000 Hz	32 kbps	224 kbps

OGG bitrate limits — Stereo (2 channels)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	16 kbps	80 kbps
12,000 Hz	16 kbps	96 kbps
16,000 Hz	24 kbps	192 kbps
24,000 Hz	32 kbps	160 kbps
48,000 Hz	48 kbps	256 kbps

Lossless formats: When outputFormat is set to WAV or FLAC, the audioSettings parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Generation Parameters

Core parameters for controlling the generated content.

model string required value: minimax:music@2.6

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required* min: 1 max: 2000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

negativePrompt string min: 1 max: 3500

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Learn more 1 resource

Text To Image: Prompts Guiding The Generation
GUIDE

seed integer min: 0 max: 1000000

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

Learn more 1 resource

Text To Image: Seed Controlling Randomness Deterministically
GUIDE

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » instrumental instrumental boolean default: false: Generate instrumental output without vocals.

settings » lyrics lyrics string min: 10 max: 1000: Structured lyrics with section tags such as [Intro], [Verse], [Chorus], [Bridge], [Outro], and [Inst]. For instrumental generation, a tag-only skeleton is acceptable.

settings » lyricsOptimizer lyricsOptimizer boolean default: false: Optimize provided lyrics or generate them from the prompt when omitted.

taskType string required value: audioInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

audioUUID string required UUID v4: UUID of the output audio.

audioURL string URI: URL of the output audio.

audioBase64Data string: Base64-encoded audio data.

audioDataURI string URI: Data URI of the output audio.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Audio

Cassette-Grit Harbor Nightdrive

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "1e21ce4e-850b-4f85-b7ba-e9bd30f5df13",
  "model": "minimax:music@2.6",
  "positivePrompt": "Warm nostalgic synth-pop with female lead vocals, 108 BPM in A minor, tape-worn drum machines, rubber bass, shimmering polysynths, distant ferry horns, reflective harbor-at-night mood, intimate verses, soaring hook, tasteful bridge, polished full-song arrangement, catchy melodic topline, 1980s cassette grit with modern mastering",
  "seed": 11492,
  "settings": {
    "lyricsOptimizer": true
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "1e21ce4e-850b-4f85-b7ba-e9bd30f5df13",
  "audioUUID": "9be2c304-0303-4672-9b86-d59a279bab47",
  "audioURL": "https://am.runware.ai/audio/os/a06dlim3/ws/5/ai/9be2c304-0303-4672-9b86-d59a279bab47.mp3",
  "seed": 11492,
  "cost": 0.15
}

Text to Audio

Glacial Cavern Pulse Drift

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "6ec2f461-da07-464a-99bd-023f1b28afc3",
  "model": "minimax:music@2.6",
  "positivePrompt": "Instrumental only, no vocals, no lyrics. A crystalline electronic ambient track with slow pulse, icy synth textures, deep sub bass, distant choir-like pads without words, subtle percussion, spacious reverb, cinematic build, 92 BPM in D minor, immersive and reflective.",
  "seed": 90798,
  "settings": {
    "instrumental": true
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "6ec2f461-da07-464a-99bd-023f1b28afc3",
  "audioUUID": "dd563b31-c6de-4c26-a417-dc9ea2241563",
  "audioURL": "https://am.runware.ai/audio/os/a03d21/ws/5/ai/dd563b31-c6de-4c26-a417-dc9ea2241563.mp3",
  "seed": 90798,
  "cost": 0.15
}

Text to Audio

Dusty Roller Rink Reverie

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "680e610a-057b-409d-8783-56f8bdf4ffb9",
  "model": "minimax:music@2.6",
  "positivePrompt": "A wistful indie-soul song at 102 BPM in A major, warm female lead vocals, rubbery bass, chiming electric piano, soft rhythm guitar, handclaps, airy analog synth, and a polished 1970s roller-rink feel with bittersweet youthful energy, catchy chorus, rich harmony stacks, intimate verses, and a triumphant final chorus.",
  "seed": 94805,
  "settings": {
    "lyrics": "[Intro]\nSkates whisper sparks on the painted floor\nOld ceiling speakers shake a little more\nSummer in the wiring, gold in the sound\nWe spin like a secret that won't slow down\n\n[Verse]\nTicket stub tucked in the pocket of my jeans\nDisco lines trembling over faded greens\nYour laugh hits the snare right ahead of the beat\nMaking the whole wide room move under my feet\nWe were all elbows, glitter, and nerve\nLearning what a small-town night could deserve\nEvery turn said stay, every echo said go\nSo we circled the center just to keep from letting go\n\n[Chorus]\nRound and round in the humming light\nHearts on wheels through a Saturday night\nIf this moment breaks, let it break in tune\nUnder paper stars and a lacquered moon\nRound and round where the slow songs start\nSilver on the floor, thunder in the heart\nWe were too young to name what we found\nSo we kept it alive by spinning around\n\n[Verse]\nSnack bar neon buzzing over cherry ice\nSomeone drew forever in the fogged-up glass twice\nThe DJ dropped the needle, the whole room leaned in\nLike every little ending could begin again\nYour hand brushed mine at the edge of the lane\nTiny as a spark, bright as a train\nI said nothing, smiling like I knew\nSome nights become a place you can roll back to\n\n[Bridge]\nWhen the lights came up, we carried the glow\nOut to the parking lot and the radio\nShoelaces loose, sky turning gray\nStill hearing the chorus on the ride away\n\n[Chorus]\nRound and round in the humming light\nHearts on wheels through a Saturday night\nIf this moment breaks, let it break in tune\nUnder paper stars and a lacquered moon\nRound and round where the slow songs start\nSilver on the floor, thunder in the heart\nWe were too young to name what we found\nSo we kept it alive by spinning around\n\n[Outro]\nSkates grow quiet, but the floor still shines\nSomewhere in the dark, that old song survives",
    "lyricsOptimizer": true
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "680e610a-057b-409d-8783-56f8bdf4ffb9",
  "audioUUID": "bb1e3c69-5c82-4f07-bd40-d17555feab97",
  "audioURL": "https://am.runware.ai/audio/os/a04d20/ws/5/ai/bb1e3c69-5c82-4f07-bd40-d17555feab97.mp3",
  "seed": 94805,
  "cost": 0.15
}

Text to Audio

Midnight Rooftop Synth Ballad

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "8cc8ec55-ac2e-4701-95f9-eeffe3698798",
  "model": "minimax:music@2.6",
  "positivePrompt": "Emotional synth-pop vocal song, 92 BPM in A minor, intimate female lead with airy harmonies, glossy analog synths, soft drum machine, warm sub bass, cinematic chorus lift, nostalgic urban night drive mood, polished studio mix, memorable hook",
  "seed": 30005,
  "settings": {
    "instrumental": false,
    "lyricsOptimizer": false,
    "lyrics": "[Intro]\nStreetlights blur like silver on the glass\nI hear the city breathing as we pass\nStatic in my chest turns into light\nI keep your name alive against the night\n\n[Verse]\nWe were sparks above the avenue below\nTrading secrets only tired hearts would know\nEvery window held a little private blaze\nWe were writing our tomorrow in the haze\nI was falling like a signal through the blue\nThen the skyline bent and pointed me to you\n\n[Chorus]\nStay with me till the speakers lose their glow\nTill the skyline is a river far below\nIf the whole world turns to echoes, let them fade\nYou and I can be the rhythm that remains\nStay with me when the last train disappears\nWhen the dark turns all our doubt into a choir\nHold me close and let the neon hum us home\nMake this rooftop feel like somewhere we belong\n\n[Verse]\nTaxi headlights draw a heartbeat on the street\nSummer wind and distant sirens keep the beat\nAll the noise becomes a halo when you smile\nAnd the hours start to vanish for a while\nI was drifting like a station out of range\nYou were magic hidden deep in something strange\n\n[Bridge]\nNo map, no warning, no perfect design\nJust your hand finding mine in the electric quiet\nIf morning comes too soon, let it wait outside\nWe've got one more song inside this sky\n\n[Chorus]\nStay with me till the speakers lose their glow\nTill the skyline is a river far below\nIf the whole world turns to echoes, let them fade\nYou and I can be the rhythm that remains\nStay with me when the last train disappears\nWhen the dark turns all our doubt into a choir\nHold me close and let the neon hum us home\nMake this rooftop feel like somewhere we belong\n\n[Outro]\nWhen the city dims, I still hear you\nIn the pulse, in the wire, in the blue"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "8cc8ec55-ac2e-4701-95f9-eeffe3698798",
  "audioUUID": "041ee046-5c9b-4d0c-8154-6701e3fced03",
  "audioURL": "https://am.runware.ai/audio/os/a05d22/ws/5/ai/041ee046-5c9b-4d0c-8154-6701e3fced03.mp3",
  "seed": 30005,
  "cost": 0.15
}