Suno

Suno V6 is Suno’s music model. On Wizzx it runs under the suno model key and is exposed as music actions: POST /api/v1/music/{action} creates songs and sounds, builds on tracks you already made, edits them, and analyzes or exports them. Every action is one asynchronous task that you poll with POST /api/v1/task/status, and each call is billed once. POST /api/v1/task/submit/suno still works and is identical to the generate action. See Submit music action for every action’s fields, mode rules, and errors.

What you can do

Group	Actions
Creation	`generate` (songs from a description or your lyrics), `inspo` (from 1–4 reference audio URLs), `sounds` (sound effects and loops), `lyrics`, `upsample-tags` (enhance a style), `upload`, `upload-cover`, `upload-extend`, `create-model` (custom model from 6–24 songs), `create-voice`
From an existing track	`extend`, `concat`, `cover`, `remaster`, `add-vocals`, `add-instrumental`, `add-stem`, `mashup`, `sample`, `persona`
Editing	`replace-section`, `remove-section`, `crop`, `fade-in`, `fade-out`, `adjust-speed`, `stems`, `stems-all`
Analysis and export	`midi`, `aligned-lyrics`, `bpm`, `music-video`, `download` (MP3, M4A, WAV)

Generate a song

generate has two modes, selected with custom:

Inspiration mode (custom: false, default): prompt is a song description of up to 3,000 characters.
Custom mode (custom: true): prompt holds the lyrics (up to 5,000 characters), plus optional title, style, negative_tags, auto_lyrics, persona_task_id, max_mode, and duration.

Parameter	Required	Accepted values
`prompt`	Conditional	Inspiration mode: required, at most 3,000 characters. Custom mode: lyrics, at most 5,000 characters; required unless `instrumental` is `true`
`custom`	No	`false` (default) or `true`
`instrumental`	No	`false` (default) or `true` for no vocals. A custom instrumental needs `prompt` or `style`
`version`	No	`v6` (default), `v6-wild`, or `v6-mini` (case-insensitive), same price
`custom_model_task_id`	No	`task_id` of your finished `create-model` task, used instead of `version`. Cannot be combined with `version` or `persona_task_id`
`persona_task_id`	No	Custom mode only. `task_id` of your finished `persona` task
`title`	No	Custom mode only, at most 80 characters
`style`	No	Custom mode only, style tags, at most 1,000 characters
`negative_tags`	No	Custom mode only, styles to avoid, at most 1,000 characters
`style_weight`, `weirdness`, `audio_weight`	No	Numbers from 0 to 1
`vocal_gender`	No	`Male` or `Female`. Not allowed with `instrumental: true`
`auto_lyrics`	No	Custom mode only, `true` or `false`
`variety`	No	`off`, `normal`, `high`, `extra`, or `max`
`max_mode`	No	Custom mode only. Higher quality at double the price
`audio_format`	No	`mp3`, `m4a`, or `wav`
`duration`	No	Custom mode only. Target length of 10–360 seconds; the actual length may differ. Does not change the price

Text limits count Unicode characters. Fields that an action does not accept, including custom-only fields sent in inspiration mode, return HTTP 422. Inspiration mode:

{
  "prompt": "Late-night city lo-fi piano with the sound of rain",
  "instrumental": true
}

Custom mode:

{
  "custom": true,
  "prompt": "[Verse]\nNeon-lit streets on a rainy night",
  "title": "Midnight Drive",
  "style": "synthwave, female vocal, cinematic",
  "negative_tags": "metal, screaming",
  "vocal_gender": "Female",
  "duration": 180
}

Submit to POST /api/v1/music/generate (or the equivalent POST /api/v1/task/submit/suno). Save the returned data.task_id and poll /api/v1/task/status. Generation usually takes 30–120 seconds.

Results

A successful task lists every generated track URL in result_urls and returns the tracks with their details in result.tracks:

{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "6f0c1c52-2a4b-4d53-9a5e-3c0f2f7d9e11",
    "status": "SUCCEEDED",
    "result_urls": [
      "https://cdn.wizzx.ai/audio/2026/10/15/track-1.mp3",
      "https://cdn.wizzx.ai/audio/2026/10/15/track-2.mp3"
    ],
    "error": "",
    "credits_deducted": 60,
    "result": {
      "tracks": [
        {
          "index": 1,
          "audio_url": "https://cdn.wizzx.ai/audio/2026/10/15/track-1.mp3",
          "image_url": "https://cdn.wizzx.ai/images/2026/10/15/cover-1.jpg",
          "title": "Midnight Drive",
          "duration": 119.8
        },
        {
          "index": 2,
          "audio_url": "https://cdn.wizzx.ai/audio/2026/10/15/track-2.mp3",
          "image_url": "https://cdn.wizzx.ai/images/2026/10/15/cover-2.jpg",
          "title": "Midnight Drive",
          "duration": 124.1
        }
      ]
    }
  },
  "request_id": "0d9d7b8e-51f6-4a1e-8d0e-9b7c2a6f4c33"
}

Do not assume exactly two tracks; iterate over result.tracks or result_urls. Other actions return lyrics, BPM, MIDI, files, a video, or IDs in result; see Music results.

Build on a track

Reference a finished track with its task’s task_id and the track’s index as audio_index. For example, extend track 2 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"
}

Then join the continuation into one song with concat. Only your own SUCCEEDED Suno tasks can be referenced. add-vocals, add-instrumental, and sample need an upload task, and concat needs an extend task. See Referencing earlier tasks.

Pricing

Each call is billed once for the whole task, regardless of how many tracks it returns. version and duration do not change the price.

Action	Credits per call	With `max_mode: true`
`generate`, `extend`, `cover`, `upload-cover`, `upload-extend`, `add-vocals`, `add-instrumental`, `add-stem`, `mashup`, `sample`, `replace-section`	60	120
`inspo`	131	262
`remaster`, `midi`	60	–
`stems`	193	–
`stems-all`	462	–
`create-model`	1,847	–
`adjust-speed`	47	–
`create-voice`	31	–
`sounds`	19	–
`lyrics`, `crop`, `fade-in`, `fade-out`, `remove-section`	16	–
`upload`, `persona`, `concat`, `music-video`, `upsample-tags`	8	–
`download`	3	–
`aligned-lyrics`, `bpm`	2	–

max_mode requires custom mode on actions that have a mode switch. Failed tasks are refunded. /pricing remains the current source of truth.

See the Submit music action reference for the machine-readable schema, and Submit Suno task for the legacy entry point.

Sources

Suno

Getting started

Agent integrations

Video Generation

Image Generation

Audio Generation

Suno

Suno

What you can do

Generate a song

Results

Build on a track

Pricing

Sources