Suno Generate Music API

suno / Suno

Generate a complete song or instrumental in simple mode, or enable custom mode for lyrics, style, title, vocal, persona, and advanced controls.

Choose the Suno model and generation mode, then direct the musical identity with only the controls that apply to that mode.

Model Type:Generate Music

Pricing

Per generation

Music task: $0.06

Model overview

Suno music generation and API workflow

Suno on sjolt provides one generate-music route for fast prompt-led generation and detailed custom composition. Choose a supported model, generate vocal or instrumental music, and retrieve every resulting track through the shared asynchronous task API.

01 · Audio generation

Simple and custom composition modes

Use a single music brief for fast exploration, or switch to custom mode to separate lyrics, style, and title. Custom mode also unlocks excluded styles, vocal guidance, influence weights, persona controls, and V5.5 duration targeting.

Supports Generate Music through simple prompting or detailed custom composition controls.
Fits song ideation, soundtrack drafts, demos, and social audio experiments.
Refine musical identity, arrangement, performance, structure, and lyrical direction before generation.

02 · Prompt direction

Choose the right Suno generation model

Select V4, a V4.5 family option, V5, or V5.5 for each request. The route enforces the prompt and style limits associated with the selected model and exposes model-specific persona and duration controls only when they apply.

Prompt-led generation

03 · API integration

Asynchronous multi-track delivery

Submit one request, keep the returned task identifier, then poll the shared status endpoint or receive a callback. Successful tasks expose all generated audio URLs for playback, download, editing, or downstream publishing workflows.

Compare available models from Alibaba, Black Forest Labs, Google, MiniMax, OpenAI, ByteDance, Kuaishou, SJolt AI, Suno, xAI in one place.
Copy the request body directly to the server to reduce frontend/backend parameter drift.
Failure states, retries, result preview, and review checkpoints stay in the same workflow.

Model characteristics

Flexible music generation through one validated API route.

Simple prompt mode

Describe the genre, mood, arrangement, vocals, structure, and lyrical subject in one concise creative brief.

Detailed custom mode

Provide lyrics, style, title, optional exclusions and vocal direction, then tune style adherence, weirdness, and audio influence.

Model-aware controls

Use persona selection on V5 or V5.5 and an optional 10-360 second duration target on V5.5, with invalid combinations rejected before submission.

Shared task lifecycle

Use the same task identifier, status polling, callback, history, and result retrieval flow as other sjolt models.

FAQ

These are the first questions to answer when evaluating this model.

Which Suno models are available?

The generate-music route supports V4, V4_5, V4_5PLUS, V4_5ALL, V5, V5_5. Select the model independently for each task.

What is the difference between simple and custom mode?

Simple mode accepts one music brief. Custom mode requires style and title, accepts lyrics for vocal music, and enables excluded styles, vocal gender, weights, persona settings, and model-specific duration control.

Can I generate instrumental music?

Yes. Set instrumental to true. In custom instrumental mode, lyrics are optional while style and title remain required.

Which controls depend on the selected model?

V4 has shorter custom style and prompt limits. Persona model selection is available only on V5 and V5.5, and duration targeting is available only on V5.5.

How are finished tracks returned?

A successful request returns a task_id. Poll the shared task endpoint or provide a top-level webhook, then read all generated audio URLs from the completed result.