Skip to main content
POST

Overview

Music to Video listens to a song, transcribes its lyrics and builds a music video around them: a visual for each part of the song, cut to the beat, with the lyrics as captions and, if you want, an audio-reactive sound wave. The song plays as the soundtrack. Sending the song. Send one of:
  • audioUrl: a public https:// link to the audio file itself (MP3, M4A, AAC, WAV or OGG), up to 10 MB, the same limit as an upload in the dashboard. Hooked downloads it and reads its type from the file. A private or local address (or a redirect to one), a bigger file, a page instead of a file (a Spotify, YouTube or Suno song page) or anything that is not audio answers 400. A Suno CDN link (https://cdn1.suno.ai/<id>.mp3) is a file and works.
  • musicId: a track from GET /v1/music/list or one of your team’s own audio files.
Not both. The song is copied into your team’s media library as a new audio file, so it counts toward your storage: a team without room for it gets 403 before anything is created.
The video follows the lyrics. A song without vocals (most of the library tracks are instrumental) cannot be transcribed: the project fails, the credits come back and your webhook gets the failure.
The visuals. mediaType as in Script to Video: ai-images (default), ai-videos, media (your own library files) or gameplay. Motion graphics are not available for this format. visualGuidelines steers the AI visuals (a setting, a palette, what to avoid) and characterIds keeps the same people across the video. With ai-videos, isContinuous chains each clip to the last frame of the one before; it is off by default, as in the dashboard.
The request answers with a projectId and status processing once the song is downloaded and checked. The transcription, the beat analysis, the media and the render happen after that. What can be refused up front (an invalid body, a link that is not audio, missing keys, too few credits, no storage left) is answered with a 400, 402 or 403 and nothing is created.

More request bodies



What happens next

  1. Keep the projectId. The project stays processing while the song is transcribed and analysed and the visuals are made; if a step fails it becomes failed, with the reason in message and the credits refunded.
  2. Either poll GET /v1/project/{projectId} until video.status is COMPLETED (or the project status is failed), or pass a webhook and wait for the call.
  3. Download the file from video.url (or data.url in the webhook).
The song stays in your media library as an audio file. See Webhooks for every payload.

Credits and your own keys

Teams on Hooked’s keys (managed): every music video costs a base (the beat analysis and the assembly). With media or gameplay that is all, taken when the project is created. With ai-images and ai-videos the media is priced once the song has been split into sections: per image by the model, or per clip by its length and model, plus the base. A team without the base gets 402 INSUFFICIENT_CREDITS and nothing is created; if the balance is short for the media later, the project fails and nothing is taken. If the project fails, the credits are refunded automatically. Teams on their own keys (BYOK): no credits are charged. The team needs these keys in Settings → AI keys:
  • OpenRouter: always (transcription, project name, images, video clips).
  • Gemini: when presetSettings.aiModel is gemini_omni_flash.
No ElevenLabs key: nothing is narrated. A missing key answers 402 missing_credentials with the list in missingProviders, before anything is created.

Errors

Send an Idempotency-Key header to retry safely: if a request times out or answers 5xx, sending it again with the same key and body returns the first answer instead of creating (and charging) the project twice.

Next Steps

Get Project

Follow the project until the video is ready

Music to Video example

More requests for this format

List Music

The library tracks you can pass as musicId

Script to Video

A narrated video with music in the background

Authorizations

x-api-key
string
header
required

Headers

Idempotency-Key
string

Makes the request safe to retry. 1-255 printable ASCII characters, one per operation (your job id, or a UUID you store), reused on every retry. Within 24 hours the same key with the same body answers with the first response and the header Idempotent-Replayed: true, without running or charging again. Keys are scoped to your team and the endpoint. 5xx answers and refusals before anything ran (401, 402, 403, 409, 429) are not kept. See Idempotency.

Required string length: 1 - 255
Pattern: ^[\x20-\x7E]+$

Body

application/json
audioUrl
string<uri>

A public https link to the song file itself (MP3, M4A, AAC, WAV or OGG, up to 10 MB), e.g. a file in your own storage or a Suno CDN link (https://cdn1.suno.ai/<id>.mp3). Hooked downloads it and reads its type from the file: a private or local address (or a redirect to one), a file over 10 MB, a page (Spotify, YouTube, a Suno song page) or anything that is not audio answers 400. Send this or musicId, not both.

Maximum string length: 2000
musicId
string

Instead of audioUrl: a track from /v1/music/list or one of your team's own audio files (up to 25 MB). The file is copied for this video. An ID that is neither answers 400 (musicId: Music "<id>" not found.). Most library tracks are instrumental: the video follows the lyrics, so use a song with vocals.

Maximum string length: 30
mediaType
enum<string>
default:ai-images

Where the visuals come from:

  • ai-images (default): one AI image per lyric section (presetSettings: preset, aiModel, characterIds).
  • ai-videos: one AI video clip per section (presetSettings: preset, quality, aiModel, isContinuous, characterIds).
  • media: your own images and videos from the media library (media required).
  • gameplay: a gameplay clip in the background (gameplaySettings).

motion-graphics is not available for this format (400).

Available options:
ai-images,
ai-videos,
media,
gameplay
presetSettings
object

Visual settings for ai-images and ai-videos; not used by media and gameplay. Each field says which media types read it.

gameplaySettings
object

mediaType: "gameplay" only: the background clip.

media
string[]

IDs of images or videos in your team's media library (max 50). Required for mediaType: "media"; ignored for the other media types. An ID that is not in your library answers 400 (media: Media "<id>" not found), and so does a media that is not COMPLETED yet.

Maximum array length: 50

Media ID from your library

name
string

Project name (max 100 characters). Generated from the song when omitted.

Maximum string length: 100
aspectRatio
enum<string>
default:ratio_9_16

Vertical, horizontal or square.

Available options:
ratio_9_16,
ratio_16_9,
ratio_1_1
language
string

Two-letter ISO 639-1 code of the song's lyrics. It guides the transcription; detected from the song when omitted.

Pattern: ^[a-zA-Z]{2}$
caption
object

Burned-in captions of the lyrics.

addStickers
boolean
default:false

Add emoji/GIF stickers anchored to the lyrics.

content
object

Branding.

webhook
string<uri>

HTTPS URL on a public host, called when the video is ready or the project fails (max 500 characters). Requests are signed: verify the Hooked-Signature header (HMAC-SHA256 of ".") with the signing secret from Settings → Webhooks; Hooked-Event and Hooked-Delivery headers name the event and the delivery. No redirects are followed; 10 s timeout; 3 immediate attempts. See the Webhooks guide for the payload.

Maximum string length: 500
metadata
object

Any JSON object of your own (max 5 KB). Stored on the project and sent back in the webhook payload. The key automationId is reserved for dashboard automations and is removed.

addSoundWave
boolean
default:true

Overlay an audio-reactive sound wave synced to the song (its style can be changed in the editor).

visualGuidelines
string

Extra direction for the AI visuals (ai-images / ai-videos): a setting, a palette, what to avoid. Max 2,000 characters.

Maximum string length: 2000

Response

Project created. Follow it with GET /v1/project/{projectId} or wait for the webhook.

success
enum<boolean>
required
Available options:
true
data
object
required
message
string
required