Music-to-Video

AI music video API for production and editable workflows

Turn Suno clips or public audio URLs into finished music videos with Fast mode, or use Studio Beta for storyboard, scene-render, selection, and finalization control.

View current credit pricing

Why teams evaluate this API

Built for music, creator, and campaign products that need an asynchronous music-to-video API with explicit spend controls and a durable project workflow.

Best-fit teams

  • • Music and creator platforms shipping automated video output
  • • Products that need editable scene workflows after initial generation
  • • Campaign teams turning finished audio into social video assets

Core capabilities

  • • Fast production path with public availability checks and automatic final MP4 storage
  • • Studio Beta storyboard, persistent scene edits, rendering, selection, and finalization
  • • Dynamic quotes and create-time media preflight, with idempotent task creation
  • • Project-level charge and refund ledger plus signed customer media links

Typical implementation flow

  1. 1Check Fast availability and request a dynamic quote
  2. 2Preflight the Suno clip or public audio URL without charging credits
  3. 3Create an idempotent Fast or Studio task and track it asynchronously
  4. 4Refresh the final signed URL or continue through Studio scene controls

Inputs, outputs, and integration limits

Create a music video from supported audio or a Suno source. Use Fast for a managed finished video and Studio for an editable production workflow. Validate the actual media before authorizing a paid create.

Fast V1
OneClick V1 accepts 10–600 seconds at 540p, 720p, or 1080p. High quality and lip-sync require at least 720p; V1 lip-sync is limited to effective sources of 180 seconds or less.
Premium V2
Explicitly select premium-v2 for 10–300 seconds at 720p. Performance modes have their own image requirements; V2 does not fall back to V1.
Cost control
Quote the settings, preflight the real source, then create with the matching preflightId and maxCredits. Preflight validates media without creating a paid task.
Delivery
Save both taskId and mvId. Read the final endpoint for readiness and a fresh temporary MP4 URL; scene edits can require recomposition.

Before creating a paid task

  • A lightweight quote does not inspect remote media. Duration and generated visual references can change the validated estimate.
  • Lyrics are planning context, not subtitle timing. Supply SRT for controlled timing or configure automatic extraction with its budget and fallback policy.
  • A character image anchors identity; it does not guarantee the same outfit or presence in every shot.
Estimate and control a music video budgetMV quote-to-download quickstart

Contract reviewed by OmnAPI Team on . Check the linked reference and current catalog before submitting requests.

View current credit pricing

FAQ

When should I use Fast instead of Studio?

Use Fast for the production one-click path. Use Studio Beta when your product needs human review, persistent scene edits, rendering choices, and controlled finalization.

How is music video pricing calculated?

Pricing is dynamic by mode, duration, resolution, selected operation, and optional features. Use the Quote API before every paid operation; for initial Fast or Studio creation, use preflight to validate media before authorizing credits.

Does the API accept uploaded audio bytes?

The public API accepts Suno clip IDs or caller-hosted public audio URLs. The first-party web app can upload an asset and then submits its resulting URL through the same MV workflow.

How long does AI music video generation take?

The create receipt may include a queue-aware estimated completion time, but delivery varies with duration, mode, and generation capacity. Production integrations should poll the Task API or use webhooks until the task is terminal.

Are finished music video URLs permanent?

No. Scene and final media use signed links. Read the MV or final endpoint again when a link expires; the media retention window is separate from link lifetime.