Generate Music

Generate, extend, cover, mashup and more — the unified music generation endpoint

POST /suno/v2/generate

cURL

cURL

curl --request POST \
  --url https://api.mountsea.ai/suno/v2/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "task": "create",
  "model": "chirp-v50",
  "make_instrumental": false,
  "prompt": "[Verse]\nHello world, here I come...\n\n[Chorus]\nLa la la...",
  "continued_aligned_prompt": "[Verse 1]\nOriginal lyrics...\n\n[Chorus]\nNew replaced lyrics...\n\n[Verse 2]\nMore lyrics...",
  "infill_lyrics": "[Bridge]\nThis is the new bridge section\nWith updated lyrics...",
  "gpt_description_prompt": "A happy pop song about summer vacation",
  "tags": "Pop, Happy, Upbeat",
  "negative_tags": "Sad, Slow",
  "title": "Summer Vibes",
  "clip_id": "clip_abc123",
  "continue_at": 30,
  "range": {
    "start_s": 15.36,
    "end_s": 53.8
  },
  "infill_type": "smart",
  "infill_context_range": {
    "start_s": 0,
    "end_s": 69.16
  },
  "persona": {
    "persona_id": "persona_xyz789",
    "artist_clip_id": "clip_abc123",
    "persona_style": "vox"
  },
  "controls": {
    "style_weight": 0.6,
    "audio_weight": 0.4,
    "weirdness_constraint": 0.2
  },
  "vocal_gender": "m",
  "audio_url": "https://example.com/audio.mp3",
  "mashup_clip_ids": [
    "clip_abc123",
    "clip_def456"
  ],
  "playlist_clip_ids": [
    "1df1d908-842d-41a2-bce4-c798a551cd2d",
    "93d2bfe9-c6d4-42cd-88fc-ee508d4fa6ed"
  ],
  "sound": {
    "description": "深沉的低音和温暖的模拟质感",
    "type": "one_shot",
    "key": "F#",
    "bpm": 2
  }
}
'

201

{
  "taskId": "15c257ff-43f7-4678-bd41-202ad6b8488b"
}

The /generate endpoint supports 15 different task types, each requiring a different set of parameters. Before calling this endpoint, we strongly recommend using the Generate Schema endpoint to get the exact required/optional fields and a complete request example for your task type.

Quick Start

1. Check required parameters

   Call GET /suno/v2/generate/schema?task=create to get the parameter schema and a request example for the create task.

   See Generate Schema →

2. Send generate request

   Call POST /suno/v2/generate with the correct parameters for your task type.

3. Poll task status

   Use the returned taskId to poll Get Task Status until status is success.

Task Types Overview

Task	Description	Key Required Fields
create	Create new music from scratch	model
extend	Extend existing music	clip_id, model
upload_extend	Extend uploaded audio	audio_url, model
upload_cover	Cover uploaded audio	audio_url, model
cover	Create cover of existing clip	clip_id, model
use_styles_lyrics	Use styles from clip with new lyrics	clip_id, model
replace_section	Replace a section of existing audio	clip_id, range, infill_context_range, continued_aligned_prompt, model
add_instrumental	Add instrumental to a range	clip_id, range, model
add_vocals	Add vocals to a range	clip_id, range, model
gen_stem_two	Generate two-track stems (vocals + instrumental)	clip_id, model
gen_stem_all	Generate all stems	clip_id, model
mashup	Mashup two songs	mashup_clip_ids, model
sample	Sample from existing clip	clip_id, range, model
inspiration	Generate from inspiration playlist	playlist_clip_ids, model
sound	Generate sound effects	sound, model

All tasks require the task and model fields. Use GET /suno/v2/generate/schema?task=xxx to get the full parameter details for any specific task type.

Common Parameters

These parameters are shared across most task types:

Parameter	Type	Description
task	string	Required. The task type (see table above)
model	string	Required. Model version: chirp-v55, chirp-v50, chirp-45+, chirp-v45, chirp-v45-lite, chirp-v40, chirp-v35
prompt	string	Lyrics or prompt text
tags	string | string[]	Style tags (e.g., "Pop, Happy, Upbeat")
negative_tags	string | string[]	Styles to exclude
title	string	Song title
make_instrumental	boolean	Generate without vocals (default: false)
vocal_gender	string	"m" (male) or "f" (female)
controls	object	Advanced control: style_weight, audio_weight, weirdness_constraint (0~1)
persona	object	Vocal persona for style mimicking

Examples

Create Music

curl -X POST https://api.mountsea.ai/suno/v2/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "task": "create",
    "model": "chirp-v55",
    "prompt": "[Verse]\nHello world, here I come...\n\n[Chorus]\nLa la la...",
    "tags": "Pop, Happy, Upbeat",
    "title": "Summer Vibes"
  }'

Not sure which parameters to pass? Call GET /suno/v2/generate/schema?task=your_task — it returns the required fields, optional fields, not-allowed fields, and a complete request example for each task type.

Try Generate Schema →

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

task · enum<string> · required

Task type. Use GET /generate/schema?task=xxx to query required fields for each task.

Available options: create, extend, upload_extend, upload_cover, cover, use_styles_lyrics, replace_section, add_instrumental, add_vocals, gen_stem_two, gen_stem_all, mashup, sample, inspiration, sound

Example:

"create"

model · string · required

Model version. Supports standard models (e.g. chirp-v50) and custom models (chirp-custom:).

Example:

"chirp-v50"

make_instrumental · boolean · default: false

Whether to make instrumental (no vocals). [Optional: all tasks]

Example:

false

prompt · string

Lyrics or prompt text. [Optional: all tasks] For replace_section: lyrics within infill_context_range (modified if replacement changes lyrics).

Example:

"[Verse]\nHello world, here I come...\n\n[Chorus]\nLa la la..."

continued_aligned_prompt · string

Full song lyrics after replacement. [Required: replace_section] Contains the complete lyrics of the entire song with the replaced section updated.

Example:

"[Verse 1]\nOriginal lyrics...\n\n[Chorus]\nNew replaced lyrics...\n\n[Verse 2]\nMore lyrics..."

infill_lyrics · string

Lyrics for the replaced section only. [Optional: replace_section] The specific lyrics within the range being replaced.

Example:

"[Bridge]\nThis is the new bridge section\nWith updated lyrics..."

gpt_description_prompt · string

Short description for GPT lyrics generation. [Optional: create, mashup, etc.]

Example:

"A happy pop song about summer vacation"

tags · string string[]

Style tags. Supports string or array. [Optional: all tasks]

Example:

"Pop, Happy, Upbeat"

negative_tags · string string[]

Negative style tags to exclude. [Optional: all tasks]

Example:

"Sad, Slow"

title · string

Song title. [Optional: all tasks]

Example:

"Summer Vibes"

clip_id · string

Source clip ID. [Required: extend, cover, use_styles_lyrics, replace_section, add_instrumental, add_vocals, gen_stem_*, sample]

Example:

"clip_abc123"

continue_at · number

Continue position in seconds. [Optional: extend, upload_extend]

Required range: x >= 0

Example:

30

range · object

Target range { start_s, end_s }. [Required: replace_section, sample] For replace_section: the section to replace (duration should be > 6 seconds). For sample: the time range to sample from source clip.

Show child attributes

Example:

{ "start_s": 15.36, "end_s": 53.8 }

infill_type · enum<string>

Infill mode for replace_section. [Optional: replace_section] "smart" = auto-select based on duration (default), "classic" = always use infill (better for long selections), "fixed" = always use fixed_infill (better for short selections).

Available options: smart, classic, fixed

Example:

"smart"

infill_context_range · object

Infill context range (must encompass range). [Required: replace_section] Should extend ~30s before range.start_s and ~30s after range.end_s. If range starts within first 30s, use 0 for start_s. If range ends within last 30s of song, use song duration for end_s.

Show child attributes

Example:

{ "start_s": 0, "end_s": 69.16 }

persona · object

Artist persona config for style mimicking. [Optional: create, cover, extend]

Show child attributes

Example:

{
  "persona_id": "persona_xyz789",
  "artist_clip_id": "clip_abc123",
  "persona_style": "vox"
}

controls · object

Advanced control sliders (0~1). [Optional: all tasks]

Show child attributes

Example:

{
  "style_weight": 0.6,
  "audio_weight": 0.4,
  "weirdness_constraint": 0.2
}

vocal_gender · enum<string>

Vocal gender (m=male, f=female). [Optional: all tasks]

Available options: m, f

Example:

"m"

audio_url · string<uri>

Audio URL for upload tasks. [Required: upload_extend, upload_cover]

Example:

"https://example.com/audio.mp3"

mashup_clip_ids · string[]

Two clip IDs for mashup [clip_a, clip_b]. [Required: mashup]

Example:

["clip_abc123", "clip_def456"]

playlist_clip_ids · string[]

Clip IDs for inspiration generation (max 4). Must be clips from the same account. [Required: inspiration]

Maximum array length: 4

Example:

[
  "1df1d908-842d-41a2-bce4-c798a551cd2d",
  "93d2bfe9-c6d4-42cd-88fc-ee508d4fa6ed"
]

sound · object

Sound generation config. [Required: sound] description is the core sound prompt (also auto-used as title). type/key/bpm are optional advanced options. Tags are auto-assembled; user-provided tags are ignored for sound task.

Show child attributes

Example:

{
  "description": "深沉的低音和温暖的模拟质感",
  "type": "one_shot",
  "key": "F#",
  "bpm": 2
}

Response

201 - application/json

taskId · string · required

task id. Use this id to query task status.

Example:

"15c257ff-43f7-4678-bd41-202ad6b8488b"