Lyric Video Maker — put a song's lyrics over your photos

This lyric video maker takes a finished song, a set of pictures and the words, and puts them together into a music video: the photos hold the frame, the lyrics appear line by line as they are sung, and a waveform can move underneath if you want a visual pulse. There is no timeline to build and no footage to shoot. You upload a track, decide where the pictures come from, check the lyrics, and export.

The pictures can be generated for you from the mood of the song, in one of seven visual styles, or they can be your own: press shots, artwork, holiday photos, anything you would want to see while the song plays. It is one of the formats in the AI music video tools from Online Vocal Remover, and the one to pick when a song needs its words on screen rather than a storyline or graphics that react to the beat.

Choose where the pictures come from. With AI images, the tool reads the mood of the track (and the lyrics, if it has them) and generates the visuals in the style you pick: Auto, Cinematic, Dreamy, Neon, Analog film, Illustrated or Minimal. You can add a short description of the subject, setting and light to steer it, and choose between standard and refined image quality. Use a single picture for the whole song, or a photo sequence of 2 to 12 images that changes with the sections of the song, each scene lasting about 20 seconds.

With your own photos, upload 1 to 12 JPEG, PNG or WebP files and drag them into the order you want. This is the option for a song that belongs to real people and places: the tool builds the video around the pictures exactly as you supplied them, and the originals are deleted once the render is complete.

Lyrics are shown as timed captions. For a track made with our AI music generator, the words and their timing can be pulled in automatically (free when precise timings already exist; a first precise-timing fetch costs 5 credits). For an uploaded song, paste the lyrics one line at a time and they are spread across the track, then adjust any line in the timeline editor, or import an LRC file if you already have one. Pick a caption style (Clean, Karaoke, Typewriter or Bold) and place the text at the top, middle or bottom of the frame.

Finish with the frame shape: 16:9 for YouTube and other landscape players, 9:16 for Shorts, Reels and TikTok. A waveform that moves with the soundtrack can be switched on or off, and the live preview in the browser shows the pictures, captions and audio together before you spend anything on a render.

The finished video is an MP4 with the original audio, ready to upload.

Upload the song. MP3, WAV, OGG and M4A files between 15 seconds and 8 minutes long, up to 50 MB, are accepted; or pick a track you already made in your account so there is nothing to upload.

Choose the pictures. Generate them from the song in one of the seven styles, as a single image or a sequence, or upload your own photos and set their order.

Check the lyrics. Pull in timed lyrics for a song made on the site, paste the words for an uploaded track, or import an LRC file, then look over the timing in the editor and choose a caption style and position.

Preview and export. Play the preview with the sound on, switch the waveform on or off, pick 16:9 or 9:16, and generate. The estimated credits are shown before you confirm, and the MP4 is ready to download when the render finishes.

Songwriters and independent artists use it to publish a lyric video for a new single without waiting for a filmed one: the artwork or a handful of photos carry the picture, and the lyrics do the rest. Anyone who has just made a song with an AI music generator uses it for the same reason; a generated track has no visuals of its own, and this gives it something to post on YouTube or TikTok in a few minutes.

It works just as well away from music releases. A birthday, wedding or memorial video is usually a favourite song and a set of photos, and the captions can carry the words of the song or a message. Teachers and choirs use it for sing-along videos, and podcasters and small labels use it to turn audio into something that plays on video platforms.

If what you want is graphics that move with the sound rather than photos and lyrics, the music visualizer is the better format: it draws bars, waves and rings that react to the audio and needs no pictures at all.