Introduction

Introduction to Suno Music Generation

Welcome to the Suno Music Generation service documentation!

This service integrates Suno AI to provide a comprehensive suite of music generation, editing, and audio processing tools. From creating original tracks to training your own custom models, Suno enables powerful end-to-end music workflows.

Supported Models

Model	Description
chirp-v55	Latest model — best quality, recommended for all tasks
chirp-v50	High-quality model, previous generation
chirp-45+	High-quality model with good performance
chirp-v45 / chirp-v45-lite	Balanced quality and speed
chirp-v40 / chirp-v35	Legacy models
chirp-custom:<uuid>	Custom models trained on your own audio via Custom Model

Features at a Glance

Music Generation

Create, extend, cover, mashup, and sample music with 15 task types via a unified /generate endpoint

Lyrics & Sound

Generate original lyrics, mashup lyrics from two songs, or create sound effects from text descriptions

Voice Persona

Create verified voice personas from your own recordings with single-task two-phase voice verification

Custom Models

Train personalized music models on 6+ audio files and use them for generation

Audio Processing

Remaster tracks, adjust speed, separate stems, concat clips, and enhance style tags

Export & Analysis

Export to MP4/WAV/MDI, get lyrics timeline, and analyze downbeats

How to Use Suno

1. Check parameters for your task

   Use the Generate Schema endpoint to get the exact required/optional fields and a request example for your task type.

2. Create a task

   Call the appropriate endpoint (e.g., Generate) with your parameters. You’ll receive a taskId.

3. Poll task status

   Use Get Task Status (GET /suno/v2/status?taskId=xxx) to poll until status is success.

4. Use the results

   The task result contains your generated audio clip data. You can then use it for further operations like export, remaster, etc.

Quick Example

Create Music

curl -X POST "https://api.mountsea.ai/suno/v2/generate" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "task": "create",
    "model": "chirp-v50",
    "tags": "Pop, Happy, Upbeat",
    "prompt": "[Verse]\nHello world, here I come\n\n[Chorus]\nLa la la...",
    "title": "Summer Vibes"
  }'

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

Try Generate Schema →

---

Available Endpoints

Core Generation

Endpoint	Method	Description
/suno/v2/generate	POST	Unified generation endpoint — supports 15 task types
/suno/v2/generate/schema	GET	Get parameter schema & examples per task type
/suno/v2/status	GET	Query task status by taskId

Lyrics

Endpoint	Method	Description
/suno/v2/lyrics	POST	Generate song lyrics from a prompt
/suno/v2/mashupLyrics	POST	Generate mashup lyrics from two songs

Audio Processing

Endpoint	Method	Description
/suno/v2/concat	POST	Concatenate audio clips
/suno/v2/remaster	POST	Remaster audio with enhanced quality
/suno/v2/adjustSpeed	POST	Adjust playback speed
/suno/v2/upsampleTags	POST	Enhance style tags with creative boost

Export & Analysis

Endpoint	Method	Description
/suno/v2/mp4	POST	Export audio as MP4 video
/suno/v2/wav	POST	Export audio as WAV
/suno/v2/mdi	POST	Download MDI data (from gen_stem_all)
/suno/v2/timing	POST	Get lyrics & audio timeline
/suno/v2/downbeats	POST	Get downbeat positions

Upload & Persona

Endpoint	Method	Description
/suno/v2/upload	POST	Upload audio file to Suno
/suno/v2/persona	POST	Create a vocal persona
/suno/v2/getVoxStem	POST	Extract vocal stem for persona creation

Voice Persona (single-task, two-phase voice verification)

Endpoint	Method	Description
/suno/v2/voicePersona/init	POST	Upload voice audio & get verification phrase (status → awaiting)
/suno/v2/voicePersona/complete	POST	Upload verification recording & create persona (same taskId)

Custom Model (3-step model training)

Endpoint	Method	Description
/suno/v2/customModel/prepare	POST	Create training session
/suno/v2/customModel/upload	POST	Upload training audio (min 6 files)
/suno/v2/customModel/create	POST	Submit for model training (100 credits)

---

Explore the API Documentation

Core

• Generate Music — Unified generation endpoint (15 task types)
• Generate Schema — Get parameter schema per task type
• Get Task Status — Poll task status

Lyrics

• Generate Lyrics — Create lyrics from a prompt
• Mashup Lyrics — Combine lyrics from two songs

Audio Processing

• Concat Audio — Concatenate clips
• Remaster — Enhance audio quality
• Adjust Speed — Change playback speed
• Upsample Tags — Enhance style tags

Export & Analysis

• Export MP4 — Download as video
• Export WAV — Download lossless audio
• Download MDI — Get MDI data
• Timeline — Lyrics & audio timeline
• Downbeats — Beat positions

Persona

• Create Persona — Create vocal persona from clip
• Get Vox Stem — Extract vocals from clip

Voice Persona

• Voice Persona Guide — Full workflow guide (single taskId, two phases)
• Init — Upload voice & get verification phrase
• Complete — Upload verification & create persona

Custom Model

• Custom Model Guide — Full 3-step workflow guide
• Prepare — Create training session
• Upload — Upload training audio
• Create — Submit for training

---

Generate Task Types

The /suno/v2/generate endpoint supports 15 task types through a single unified interface:

Task	Description
create	Create new music from scratch
extend	Extend existing music from a position
upload_extend	Extend uploaded external audio
upload_cover	Cover uploaded external audio
cover	Create cover of existing clip
use_styles_lyrics	Use styles from clip with new lyrics
replace_section	Replace a section of existing audio
add_instrumental	Add instrumental to a time range
add_vocals	Add vocals to a time range
gen_stem_two	Separate into vocals + instrumental
gen_stem_all	Separate into all stems
mashup	Mashup two songs together
sample	Sample from an existing clip
inspiration	Generate from an inspiration playlist
sound	Generate sound effects

Each task requires different parameters. Use Generate Schema to get the exact fields for each task type.