Skip to main content
For coding agents, discover the current recommended music shortlist first with GET /v1/models?recommended_for=music, then send the selected model explicitly to this endpoint.
Generate music and lyrics using AI. This is an asynchronous API. Create responses return a task identity, and may also return a preferred poll_url for status checks.

​
Request Body

​
model
string
default:"suno_music"
Model to use: suno_music for music generation, suno_lyrics for lyrics only.
​
prompt
string
required
Description of the music to generate. Can include style, mood, instruments, etc.
​
title
string
Title for the generated song.
​
tags
string
Style tags (e.g., “pop, upbeat, electronic”).
​
action
string
Generation type: MUSIC (default) or LYRICS.
​
mv
string
Model version to use.
​
continue_clip_id
string
ID of a previous clip to continue from.
​
continue_at
number
Timestamp (in seconds) to continue from.
​
user
string
A unique identifier for the end-user.

​
Response

​
id
string
Task ID for polling status.
​
task_id
string
Async task identifier alias when returned by the adapter.
​
poll_url
string
Preferred polling URL for this task when provided.
​
status
string
Task status: pending, processing, completed, or failed.
​
created
integer
Unix timestamp of task creation.
curl -X POST "https://api.lemondata.cc/v1/music/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "suno_music",
    "prompt": "An upbeat electronic dance track with heavy bass",
    "title": "Night Drive",
    "tags": "electronic, EDM, energetic"
  }'

{
  "id": "music_abc123",
  "task_id": "music_abc123",
  "poll_url": "/v1/music/generations/music_abc123",
  "status": "pending",
  "created": 1706000000,
  "model": "suno_music"
}