Submit music action

curl --request POST \
  --url https://api.wizzx.ai/api/v1/music/{action} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "custom": true,
  "prompt": "[Verse]\nNeon-lit streets on a rainy night",
  "title": "Midnight Drive",
  "style": "synthwave, female vocal"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "model_key": "<string>",
    "credits_deducted": 1,
    "action": "<string>",
    "provider_task_id": "<string>",
    "provider_key": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

POST

api

music

{action}

curl --request POST \
  --url https://api.wizzx.ai/api/v1/music/{action} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "custom": true,
  "prompt": "[Verse]\nNeon-lit streets on a rainy night",
  "title": "Midnight Drive",
  "style": "synthwave, female vocal"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "model_key": "<string>",
    "credits_deducted": 1,
    "action": "<string>",
    "provider_task_id": "<string>",
    "provider_key": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

{
  "error": {
    "message": "<string>",
    "type": "invalid_request_error",
    "param": "<string>",
    "code": "<string>"
  },
  "request_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "retry_after": 1
}

Overview

POST /api/v1/music/{action} is the main entry point for Suno music. The path names one of 33 actions. Every action creates one asynchronous task of the suno model: save data.task_id, then poll POST /api/v1/task/status until the task finishes. Each call is billed once; see credits per action. POST /api/v1/task/submit/suno still works and is identical to the generate action.

curl --fail-with-body --silent --show-error \
  -X POST https://api.wizzx.ai/api/v1/music/generate \
  -H "Authorization: Bearer <api_key>" \
  -H "Content-Type: application/json" \
  --data '{
    "custom": true,
    "prompt": "[Verse]\nNeon-lit streets on a rainy night",
    "title": "Midnight Drive",
    "style": "synthwave, female vocal"
  }'

The response uses the usual submit envelope and adds action:

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "6f0c1c52-2a4b-4d53-9a5e-3c0f2f7d9e11",
    "model_key": "suno",
    "action": "generate",
    "credits_deducted": 60
  },
  "request_id": "0d9d7b8e-51f6-4a1e-8d0e-9b7c2a6f4c33"
}

Rules for every action

Strict fields. Each action accepts only the fields listed for it below. Sending a music field that the action does not accept returns HTTP 422 validation_failed, for example music action bpm does not accept version. Omit fields you do not need.
An unknown action returns HTTP 404 music_action_not_found.
Text limits count Unicode characters. Audio URLs must be public HTTP(S) URLs of at most 2,048 characters.
Earlier tasks are referenced only by their Wizzx task_id. See Referencing earlier tasks.
Music actions share the submit rate limit. Validation and source-task errors are returned before any credits are reserved.

Shared fields

These fields mean the same thing in every action that accepts them.

Field	Type	Rules
`prompt`	string	Lyrics in custom mode, at most 5,000 characters. A description of at most 3,000 characters for `generate` inspiration mode, the `lyrics` topic, and the `sounds` description
`gpt_description`	string	Song description for inspiration mode (`custom: false`) on actions other than `generate`, at most 3,000 characters
`custom`	boolean	Custom (lyrics) mode switch. See Custom and inspiration mode
`instrumental`	boolean	`true` for no vocals. Cannot be combined with `vocal_gender`
`version`	string	`v6` (default), `v6-wild`, or `v6-mini`, case-insensitive, same price
`custom_model_task_id`	string	`task_id` of your finished `create-model` task. Use it instead of `version`; cannot be combined with `version` or `persona_task_id`
`persona_task_id`	string	`task_id` of your finished `persona` or `create-voice` task. Custom mode only
`title`	string	At most 80 characters
`style`	string	Style tags, at most 1,000 characters
`negative_tags`	string	Styles to avoid, at most 1,000 characters
`style_weight`, `weirdness`, `audio_weight`	number	0–1; `0` is a valid value
`vocal_gender`	string	`Male` or `Female` (`m` and `f` are accepted). Not allowed with `instrumental: true`
`auto_lyrics`	boolean	Custom mode only
`variety`	string	`off`, `normal`, `high`, `extra`, or `max`
`max_mode`	boolean	Higher quality at double the price. Requires custom mode on actions that have a mode switch
`audio_format`	string	`mp3`, `m4a`, or `wav`
`duration`	integer	Target length of 10–360 seconds; the actual length may differ. Does not change the price
`task_id`	string	Source task. See Referencing earlier tasks
`audio_index`	integer	1–20, default `1`: the `result.tracks[].index` of the source track

The action tables below use these shorthands:

Model choice: version or custom_model_task_id
Style fields: title, style, negative_tags
Weights: style_weight, weirdness, audio_weight
Mode fields: custom, prompt, gpt_description

Custom and inspiration mode

Some actions switch between custom mode, where you write lyrics and style, and inspiration mode, where Suno works from a description.

Action	How the mode is chosen
`generate`	`custom` defaults to `false`. Inspiration mode: `prompt` is a required song description. Custom mode: `prompt` holds lyrics and is required unless `instrumental` is `true`; a custom instrumental needs `prompt` or `style`
`upload-cover`	`custom` is required. `false` needs `gpt_description`; `true` needs `prompt` unless `instrumental` is `true`
`extend`	`custom` defaults to `true`. `false` needs `gpt_description`
`cover`, `add-vocals`, `add-instrumental`, `add-stem`, `mashup`, `sample`	When `custom` is omitted it is inferred: `prompt` means custom; otherwise `gpt_description` means inspiration; otherwise `style` or `title` means custom; with none of them the request returns 422. `mashup` and `sample` in custom mode need `prompt` unless `instrumental` is `true`
`upload-extend`	Always custom mode; there is no `custom` field

In inspiration mode, generate rejects title, style, negative_tags, auto_lyrics, persona_task_id, duration, and max_mode. The other actions reject prompt, title, style, negative_tags, auto_lyrics, persona_task_id, duration, max_mode, style_weight, and audio_weight. In custom mode, gpt_description is rejected.

Referencing earlier tasks

Many actions build on a track you already generated:

task_id + audio_index select one track. audio_index is the 1-based index of the track in the source task’s result.tracks and defaults to 1.
mashup uses task_ids (exactly two tasks) and audio_indexes (two entries, default [1, 1]) instead.
custom_model_task_id must point to a finished create-model task, and persona_task_id to a finished persona or create-voice task.

Every referenced task must be your own suno task with status SUCCEEDED. Only actions that produce tracks can be a track source: generate, inspo, sounds, upload, upload-cover, upload-extend, extend, cover, remaster, stems, stems-all, add-vocals, add-instrumental, add-stem, replace-section, remove-section, crop, fade-in, fade-out, adjust-speed, concat, mashup, and sample. Lyrics, style, analysis, persona, model, voice, video, and download results cannot. Some actions need a specific kind of source:

Action	Source task must be
`add-vocals`, `add-instrumental`, `sample`	An `upload` task
`concat`	An `extend` task

Before charging, the gateway also checks that audio_index exists in the source task and that continue_at, end_s, and fade_duration fit the source track’s duration. Any failed check returns HTTP 422 and no credits are reserved.

Tasks that finished before October 15, 2026 have no result object. They can still be used as sources, but the track index and times cannot be checked in advance; an out-of-range value then fails the task and its credits are refunded.

Actions

All actions return their output in the task status result object.

Creation

Action	Required	Optional	Result
`generate`	`prompt`, except for a custom-mode instrumental (modes)	`custom`, `instrumental`, model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`, `duration`	`tracks`, usually two
`inspo`	`audio_urls`: 1–4 public reference audio URLs	`prompt` (lyrics), model choice, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`	`tracks`
`sounds`	`prompt`: sound description	`version`, `sound_type` (`one-shot` or `loop`), `bpm` (integer 1–300), `key` (`C` to `B` in sharp notation such as `F#`, add `m` for minor such as `C#m`), `audio_format`	`tracks`
`lyrics`	`prompt`: topic	`lyrics_model` (`classic` or `remi`)	`lyrics`
`upsample-tags`	`style`	–	`style` (enhanced)
`upload`	`audio_url`	–	`tracks`; a track may have no `audio_url`. Use the task as the source for `add-vocals`, `add-instrumental`, and `sample`
`upload-cover`	`audio_url` (shorter than 8 minutes), `custom`	mode fields, `instrumental`, model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`, `duration`	`tracks`
`upload-extend`	`audio_url`, `continue_at` (at least 1 second)	`prompt` (lyrics), model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`, `duration`	`tracks`
`create-model`	`name` (at most 80 characters), `audio_urls`: 6–24 public audio URLs	–	`model_id`. Use this task’s `task_id` as `custom_model_task_id`. Can take about 20 minutes
`create-voice`	`audio_url` (MP3 or WAV): a clean vocal recording without music	–	`persona_id`; use this task’s `task_id` as `persona_task_id`

From an existing track

These actions take task_id (required) and audio_index (optional) unless noted.

Action	Required besides `task_id`	Optional	Source	Result
`extend`	`continue_at`: at least 1 second and less than the track duration	mode fields (`custom` defaults to `true`), model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`, `duration`	Any track	`tracks`
`concat`	–	`audio_format`	`extend` task	`tracks`: the full joined song
`cover`	Mode (inferred)	mode fields, model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `variety`, `max_mode`, `audio_format`, `duration`	Any track	`tracks`
`remaster`	–	`variation_category` (`subtle`, `normal`, or `high`), `audio_format`	Any track	`tracks`
`add-vocals`	Mode (inferred)	mode fields, model choice, style fields, weights, `vocal_gender`, `variety`, `max_mode`, `audio_format`	`upload` task	`tracks`
`add-instrumental`	Mode (inferred)	Same as `add-vocals`	`upload` task	`tracks`
`add-stem`	Mode (inferred)	mode fields, model choice, style fields, weights, `variety`, `max_mode`, `audio_format`	Any track	`tracks`
`mashup`	`task_ids`: exactly two tasks, instead of `task_id`; mode (inferred)	`audio_indexes` (two entries, default `[1, 1]`), mode fields, `instrumental`, model choice, `persona_task_id`, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`	Two tracks	`tracks`
`sample`	`start_s`, `end_s`; mode (inferred)	mode fields, `instrumental`, model choice, style fields, weights, `vocal_gender`, `auto_lyrics`, `variety`, `max_mode`, `audio_format`	`upload` task	`tracks`
`persona`	`name` (at most 80 characters)	`description` (at most 1,000 characters), `style`, `start_s` / `end_s` (vocal clip)	Any track	`persona_id`. Use this task’s `task_id` as `persona_task_id`

Editing

All editing actions take task_id (required) and audio_index (optional) and accept any track as the source.

Action	Required besides `task_id`	Optional	Result
`replace-section`	`start_s`, `end_s`	`infill_lyrics` (new lyrics for the section, at most 5,000 characters), `prompt` (surrounding lyrics for context), model choice, style fields, `variety`, `max_mode`, `audio_format`	`tracks`
`remove-section`	`start_s`, `end_s`	–	`tracks`
`crop`	`start_s`, `end_s`: the part to keep	–	`tracks`
`fade-in`, `fade-out`	`fade_duration`: greater than 0 and not longer than the track	`title`	`tracks`
`adjust-speed`	`speed`: 0.25–4	`keep_pitch` (default `true`), `title`	`tracks`
`stems`	–	`stem_type` (default `lead_vocal`; more than 90 values such as `drum_kit`, `bass`, `piano`, `808`; see the API schema for the full list), `audio_format`	`tracks`
`stems-all`	–	`audio_format`	`tracks`, one per stem

Time ranges are in seconds and must satisfy 0 ≤ start_s < end_s ≤ track duration.

Analysis and export

These actions take task_id (required) and audio_index (optional) and accept any track as the source.

Action	Required besides `task_id`	Result
`midi`	–	`midi`
`aligned-lyrics`	–	`aligned_lyrics`: lyrics with timing
`bpm`	–	`bpm`: `{avg, min, max}`
`music-video`	–	`video_url`: MP4
`download`	`formats`: one or more of `mp3`, `m4a`, `wav`; duplicates are ignored	`files`

Worked examples

Each step is a separate paid task. Wait until a task is SUCCEEDED before you reference it.

Generate, extend, and join into one song

Step 1. Generate with POST /api/v1/music/generate:

{
  "custom": true,
  "prompt": "[Verse]\nNeon-lit streets on a rainy night",
  "title": "Midnight Drive",
  "style": "synthwave, female vocal"
}

Poll the task and pick a track from result.tracks, for example the one with "index": 2. Step 2. Extend that track from 1:30 with POST /api/v1/music/extend:

{
  "task_id": "6f0c1c52-2a4b-4d53-9a5e-3c0f2f7d9e11",
  "audio_index": 2,
  "continue_at": 90,
  "prompt": "[Bridge]\nThe city fades behind us"
}

Step 3. Join the continuation into a full song with POST /api/v1/music/concat, using the task_id of the extend task:

{
  "task_id": "8a1d2e44-5b6c-4f70-8e91-a2b3c4d5e6f7"
}

Add vocals to your own audio

Step 1. Upload the audio with POST /api/v1/music/upload:

{
  "audio_url": "https://example.com/beat.mp3"
}

Step 2. Add vocals with POST /api/v1/music/add-vocals, using the task_id of the upload task:

{
  "task_id": "3c9e7f10-2d4b-4a8e-9f61-7b2c1d0e5a94",
  "prompt": "[Verse]\nMorning light on an empty street",
  "style": "soul, female vocal"
}

Separate stems and download files

Extract one stem from a finished song with POST /api/v1/music/stems:

{
  "task_id": "6f0c1c52-2a4b-4d53-9a5e-3c0f2f7d9e11",
  "stem_type": "drum_kit"
}

Use stems-all instead to split the track into every stem. To get WAV and MP3 files of a track, call POST /api/v1/music/download:

{
  "task_id": "6f0c1c52-2a4b-4d53-9a5e-3c0f2f7d9e11",
  "formats": ["wav", "mp3"]
}

The finished task lists the files in result.files, in request order.

Errors

HTTP	Meaning
402	Insufficient credits
404	`music_action_not_found`: unknown action
422	`validation_failed`: a field the action does not accept, a mode rule, a length, range, or enum violation, or an unusable source task (not found, not yours, not finished, wrong action, or index or time out of range)
429	Rate limited
503	`model_unavailable`: Suno is not accepting new tasks

See Error codes for the error format and retry guidance.

Authorizations

Authorization

string

header

required

Wizzx API key. This is not a JWT.

Path Parameters

action

enum<string>

required

Music action. Unknown actions return 404 music_action_not_found.

Available options:

generate,

inspo,

sounds,

lyrics,

upsample-tags,

upload,

upload-cover,

upload-extend,

create-model,

create-voice,

extend,

concat,

cover,

remaster,

add-vocals,

add-instrumental,

add-stem,

mashup,

sample,

persona,

replace-section,

remove-section,

crop,

fade-in,

fade-out,

adjust-speed,

stems,

stems-all,

midi,

aligned-lyrics,

bpm,

music-video,

download

Body

application/json

Request body for POST /api/v1/music/{action}. Each action accepts only its own fields, listed per action in x-wizzx-music-actions; sending a field the action does not accept returns 422. Earlier tasks are referenced by Wizzx task_id only and must be your own SUCCEEDED suno tasks.

prompt

string

Lyrics in custom mode (at most 5000 characters). A description (at most 3000 characters) for generate inspiration mode, the lyrics topic, and the sounds description.

Maximum string length: 5000

gpt_description

string

Song description for inspiration mode (custom=false) on actions other than generate.

Maximum string length: 3000

custom

boolean

Custom (lyrics) mode. generate defaults to false; extend defaults to true; upload-cover requires it; cover, add-vocals, add-instrumental, add-stem, mashup, and sample infer it when omitted (prompt, style, or title means true; gpt_description means false).

instrumental

boolean

default:false

No vocals. Cannot be combined with vocal_gender.

version

enum<string>

default:v6

Case-insensitive. All versions cost the same. Cannot be combined with custom_model_task_id.

Available options:

v6,

v6-wild,

v6-mini

custom_model_task_id

string<uuid>

task_id of your SUCCEEDED create-model task. Replaces version; cannot be combined with version or persona_task_id.

persona_task_id

string<uuid>

task_id of your SUCCEEDED persona or create-voice task. Custom mode only.

title

string

Custom mode only on actions with a mode switch.

Maximum string length: 80

style

string

Style tags. Custom mode only on actions with a mode switch. Required by upsample-tags.

Maximum string length: 1000

negative_tags

string

Styles to avoid. Custom mode only on actions with a mode switch.

Maximum string length: 1000

style_weight

number

How strongly to follow style, 0-1. Custom mode only on actions other than generate.

Required range: 0 <= x <= 1

weirdness

number

How experimental the result is, 0-1.

Required range: 0 <= x <= 1

audio_weight

number

How closely to follow the source audio, 0-1. Custom mode only on actions other than generate.

Required range: 0 <= x <= 1

vocal_gender

enum<string>

Case-insensitive; m and f are accepted. Cannot be combined with instrumental=true.

Available options:

Male,

Female

auto_lyrics

boolean

default:false

Custom mode only.

variety

enum<string>

Available options:

off,

normal,

high,

extra,

max

max_mode

boolean

default:false

Higher quality at double the price. Requires custom mode on actions with a mode switch.

audio_format

enum<string>

Available options:

mp3,

m4a,

wav

duration

integer

Target length in seconds; actual length may differ. Custom mode only on actions with a mode switch. Does not change the price.

Required range: 10 <= x <= 360

task_id

string<uuid>

Source task: one of your SUCCEEDED suno tasks that produced tracks.

audio_index

integer

default:1

1-based result.tracks[].index of the source task.

Required range: 1 <= x <= 20

task_ids

string<uuid>[]

mashup: exactly two source tasks.

Required array length: 2 elements

audio_indexes

integer[]

mashup: track index for each task_ids entry.

Required array length: 2 elements

Required range: 1 <= x <= 20

audio_url

string<uri>

Publicly reachable HTTP(S) audio URL, at most 2048 characters.

Maximum string length: 2048

Pattern: ^https?://

audio_urls

string<uri>[]

inspo: 1-4 reference audio URLs. create-model: 6-24 training audio URLs.

Required array length: 1 - 24 elements

Publicly reachable HTTP(S) audio URL, at most 2048 characters.

Maximum string length: 2048

Pattern: ^https?://

continue_at

number

Seconds into the source audio where the continuation starts. For extend it must be less than the source track duration.

Required range: x >= 1

start_s

number

Section start in seconds.

Required range: x >= 0

end_s

number

Section end in seconds. Greater than start_s and not beyond the source track duration.

Required range: x > 0

fade_duration

number

Fade length in seconds; not longer than the source track.

Required range: x > 0

speed

number

Required range: 0.25 <= x <= 4

keep_pitch

boolean

default:true

stem_type

enum<string>

default:lead_vocal

Case-insensitive.

Available options:

lead_vocal,

drum_kit,

bass,

backing_vocals,

piano,

electric_guitar,

percussion,

string_section,

synth,

acoustic_guitar,

sound_effects,

synth_pad,

synth_bass,

guitar,

brass_section,

organ,

electronic_drum_kit,

lead_electric_guitar,

synth_keys,

rhythm_electric_guitar,

electric_piano,

upright_bass,

keyboards,

distorted_electric_guitar,

kick,

snare,

risers,

synth_strings,

synth_lead,

woodwinds,

flute,

harp,

tambourine,

trumpet,

arpeggiator,

accordion,

fiddle,

pedal_steel_guitar,

synth_voice,

violin,

digital_piano,

synth_brass,

mandolin,

choir,

banjo,

bells,

clarinet,

tenor_saxophone,

trombone,

shaker,

french_horn,

glockenspiel,

electric_bass,

cello,

timpani,

harmonica,

marimba,

vibraphone,

lap_steel_guitar,

saxophone,

orchestra,

horns,

cymbals,

hand_clap,

oboe,

celesta,

congas,

drone,

alto_saxophone,

double_bass,

ukulele,

harpsichord,

baritone_saxophone,

xylophone,

tuba,

bass_guitar,

whistle,

lead_guitar,

rhodes,

808,

bongos,

bassoon,

cowbell,

viola,

sitar,

steel_drums,

piccolo,

theremin,

bagpipes,

hi_hat,

music_box,

melodica,

tabla,

koto,

djembe,

taiko,

didgeridoo

infill_lyrics

string

replace-section: lyrics for the replaced section.

Maximum string length: 5000

variation_category

enum<string>

Available options:

subtle,

normal,

high

sound_type

enum<string>

Available options:

one-shot,

loop

bpm

integer

Required range: 1 <= x <= 300

key

enum<string>

Sharp notation; append m for minor.

Available options:

C,

Cm,

C#,

C#m,

D,

Dm,

D#,

D#m,

E,

Em,

F,

Fm,

F#,

F#m,

G,

Gm,

G#,

G#m,

A,

Am,

A#,

A#m,

B,

Bm

lyrics_model

enum<string>

Available options:

classic,

remi

name

string

create-model or persona name.

Maximum string length: 80

description

string

persona description.

Maximum string length: 1000

formats

enum<string>[]

Duplicates are ignored.

Minimum array length: 1

Available options:

mp3,

m4a,

wav

Response

Task accepted

code

enum<integer>

required

Available options:

0

message

string

required

Example:

"success"

data

object

required

Show child attributes

request_id

string<uuid>

required

Overview

Video Generation

Image Generation

Audio Generation

Task Management

Submit music action

Overview

Rules for every action

Shared fields

Custom and inspiration mode

Referencing earlier tasks

Actions

Creation

From an existing track

Editing

Analysis and export

Worked examples

Generate, extend, and join into one song

Add vocals to your own audio

Separate stems and download files

Errors

Authorizations

Path Parameters

Body

Response

​Overview

​Rules for every action

​Shared fields

​Custom and inspiration mode

​Referencing earlier tasks

​Actions

​Creation

​From an existing track

​Editing

​Analysis and export

​Worked examples

​Generate, extend, and join into one song

​Add vocals to your own audio

​Separate stems and download files

​Errors

Authorizations

Path Parameters

Body

Response

Overview

Rules for every action

Shared fields

Custom and inspiration mode

Referencing earlier tasks

Actions

Creation

From an existing track

Editing

Analysis and export

Worked examples

Generate, extend, and join into one song

Add vocals to your own audio

Separate stems and download files

Errors