Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

WaveSpeed Music Video Generator

WaveSpeed Music Video Generator creates performance videos from songs, using vocal phrasing to organize scene changes and synchronize singing across varied camera angles.

Text to video

Based on verified input duration.

OfferingPrice (USD)
Resolution: 480p$0.03 / input second
Resolution: 720p$0.06 / input second
  • Images count: 0, 1, 2, 3 (same price).
  • Based on the audio input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 600 seconds.
  • Bill at least 3 seconds.
  • Round the total charge up to the next $0.01.

WaveSpeed Music Video Generator

WaveSpeed Music Video Generator builds a music video around supplied audio. Optional reference images establish the person appearing in the footage, and a written description guides the setting and performance. The assembled video combines generated scenes with the original track.

Vocal phrases and pauses help determine where scenes change. Scene planning covers camera angles, framing, and expressions, while the performance animation aligns mouth movement with singing. Transitions connect those scenes into an edited sequence whose structure follows the song.

What it's good for

Musicians can use it to create performance-led visuals for a recorded track, with the singer appearing in different compositions throughout the video. It also suits promotional song content and visual treatment exploration: a scene description establishes a creative direction, reference imagery supplies the performer’s appearance, and the audio gives the sequence its musical timing. Editors can assess how that combination supports the mood and phrasing of the song.

Model ID

wavespeed-ai/music-video-generator

Output Type

Video

Pricing

From $0.03 / input second

Provider

WaveSpeed

Hosting

Passthru

WaveSpeed Music Video Generator

WaveSpeed Music Video Generator builds a music video around supplied audio. Optional reference images establish the person appearing in the footage, and a written description guides the setting and performance. The assembled video combines generated scenes with the original track.

Vocal phrases and pauses help determine where scenes change. Scene planning covers camera angles, framing, and expressions, while the performance animation aligns mouth movement with singing. Transitions connect those scenes into an edited sequence whose structure follows the song.

What it's good for

Musicians can use it to create performance-led visuals for a recorded track, with the singer appearing in different compositions throughout the video. It also suits promotional song content and visual treatment exploration: a scene description establishes a creative direction, reference imagery supplies the performer’s appearance, and the audio gives the sequence its musical timing. Editors can assess how that combination supports the mood and phrasing of the song.