Skip to content

Lyric Video Maker

Turn a vocal track into a captioned music video with generated scene images. Choose caption styling and placement, then confirm the generation quote.

Lyric Video Maker

Video audio

Drop your audio here or choose a file

MP3, WAV, OGG, M4A, AAC and FLAC where supported by your browser. Up to 50 MB and 15 minutes.

AI photo video

No captions yet. Use the song's captions, import an LRC file, or run Auto captions below.

Caption alignment

Generate images from your audio, then assemble a video using the current caption and waveform settings. Check the price before starting.

Audio and caption preview

Choose audio to preview timing and caption placement. Generated photo videos appear in My videos.

Automatic vocal transcription16:9 or 9:16 canvasCaption styling and placementOptional audio waveformUpload a track or choose My Music

Three visualizer renders of the reference tracks

These clips were produced by this tool, one per reference track. Two run the full 45-second excerpt while the first is 16 seconds because that source recording is short; all are 720p with the waveform on and captions off, as none of the tracks has timed lyrics.

Built for audio creators

Who puts the words on screen

Spoken-word creators

Pair a short spoken recording with readable captions and generated scene images.

Songwriters sharing demos

Help listeners follow the words of a vocal demo before a filmed performance is ready.

Independent artists

Create a lyric-focused release with a consistent visual treatment and a horizontal or vertical canvas.

Create a captioned clip with the Lyric Video Maker

1

Start with a vocal recording

Upload your finished song or select an owned track from My Music. The workflow transcribes this audio rather than asking you to paste lyrics.

2

Set the caption presentation

Keep lyrics enabled, select a caption preset and choose top, middle or bottom placement. Pick an image treatment and decide whether to display the waveform.

3

Confirm the quote and review the video

Review the credit amount before generation. Open My videos to check the finished captions and download the MP4.

Lyric Video Maker timing and presentation

The Lyric Video Maker combines vocal transcription, image planning and video rendering. It keeps available word start and end times, including gaps between sung phrases.

Sound designer analyzing BPM key and pitch before editing audio

Words follow the recorded vocal

Aligned words can be highlighted as they are sung. If word alignment is unavailable for a phrase, its full line uses the returned segment timing.

Generated scene backgrounds

Single-image mode holds one generated scene; multiple-image mode creates a sequence, capped at 32 images. The photo-style selection guides its visual treatment.

An optional reactive waveform

Turn the waveform on for visible audio movement or off to keep attention on the text. Scene cuts use evenly distributed intervals, not detected beat positions.

What a lyric video render needs

Lyric Video Maker inputs and output

1 source recording

Automatic transcription follows the audio you selected.

2 canvas ratios

Landscape 16:9 and portrait 9:16.

6 upload formats

MP3, WAV, OGG, M4A, FLAC and AAC.

1 MP4 per task

Audio may be up to 50 MB and 15 minutes; finished exports appear in My videos.

Where Lyric Video Maker results go next

AI Music Generator

AI Mastering

AI Music Visualizer

Music Video: Visualizer

AI Music Video

Lyric Video Maker questions

Answers about transcription, caption accuracy, audio inputs and generation credits.

Make the words part of your music video

Choose a vocal track, set the caption presentation and review your quote.

Open the lyric video makerExplore video tools