Skip to main content
POST
/
ai
/
sn
/
audio
/
generate
suno generate audio
curl --request POST \
  --url https://ai.pmock.com/api/ai/sn/audio/generate \
  --header 'Content-Type: application/json' \
  --data '
{
  "task": "create",
  "model": "chirp-v35",
  "makeInstrumental": false,
  "prompt": "<string>",
  "continuedAlignedPrompt": "<string>",
  "infillLyrics": "<string>",
  "gptDescriptionPrompt": "<string>",
  "tags": "<string>",
  "negativeTags": "<string>",
  "title": "<string>",
  "clipId": "<string>",
  "continueAt": 123,
  "range": {
    "start": 123,
    "end": 123
  },
  "infillContextRange": {
    "start": 123,
    "end": 123
  },
  "persona": {
    "personaId": "<string>",
    "artistClipId": "<string>"
  },
  "controls": {
    "styleWeight": 123,
    "audioWeight": 123,
    "weirdnessConstraint": 123
  },
  "vocalGender": "m"
}
'
{
  "code": 200,
  "message": "<string>",
  "data": {
    "taskId": "<string>"
  },
  "traceId": "<string>"
}

Body

application/json

SN-Generate audio request parameters

task
enum<string>
required

Task type

Available options:
create,
extend,
upload_extend,
upload_cover,
cover,
use_styles_lyrics,
replace_section,
add_instrumental,
add_vocals,
gen_stem_two,
gen_stem_all
Example:

"create"

model
enum<string>
required

Model

Available options:
chirp-v35,
chirp-v40,
chirp-v45,
chirp-45+,
chirp-v45-lite,
chirp-v50
Example:

"chirp-v35"

makeInstrumental
boolean
default:false

Whether to make musical instruments

Example:

false

prompt
string

If the lyrics prompt is set, the model will create based on the prompt

continuedAlignedPrompt
string

Align lyrics for continuation (recommended for task=replace_dection))

infillLyrics
string

Lyrics filling text (used when task=replace_dection)

gptDescriptionPrompt
string

Generate lyrics using GPT; Provide only brief descriptive prompts

tags
string

Song style tags, comma separated strings or string arrays

negativeTags
string

Negative song style labels. Comma separated string or array

title
string

Song title

clipId
string

clip_id Used to continue or reference from existing audio

continueAt
integer<int32>

Continue position in seconds (extend,upload_extend)

range
object

The target range of replace_dection or add_ * task, end_2 should be>=start_2

infillContextRange
object

only used for the target range of task replace_dection, infill_comtext_range. End_2 should be>=start_2

persona
object

artist role configuration. Provide 'persona_id' and 'artist_clip_id' to mimic style

controls
object

advanced control through sliders. All values are between 0 and 1. If omitted, use default value

vocalGender
enum<string>

voice gender

Available options:
m,
f

Response

200 - */*

OK

Unified return structure for response results

code
integer<int32>

Response status code

Example:

200

message
string

Response message

data
object

Response result

traceId
string

Response traceId