Upload a song and this lyric video generator transcribes the vocal, times each word to the moment it is sung, and lays the lyrics over AI-generated scenes that follow what the song is about. You get a vertical clip for Reels and TikTok or a 16:9 lyric video for YouTube, with your original audio as the only sound.
Lyric videos are made in the Music to Video format. Upload your song there, set sync to lyrics, and the price shows before you render.
A 9:16 render from the Music to Video format, the same format lyric videos are made in: the uploaded track is transcribed and AI scenes are cut to it.
The landscape version of the format for full-length uploads, where the minimal caption style keeps lyrics readable without covering the scenes.
Add the finished track. Mention anything the audio does not make obvious in the track details field, such as "chorus repeats at 1:10" or "second verse is darker".
Choose lyrics in the sync setting so scenes change with the words, then pick a caption style and a scene style that fit the genre.
Watch the render, correct any misheard word in Studio, and download the MP4 for YouTube, TikTok or Reels.
The vocal is transcribed with word timings, so each word appears and highlights as it is sung. Transcription can miss a word on a heavy mix or a fast verse. After the render, the Studio editor lets you correct any caption word by word and re-render, so the final lyric video says exactly what you wrote.
Lyric video templates usually mean a fixed animation you drop text into. Here the look comes from caption styles and scene styles instead. Karaoke highlight lights up each word as it is sung, minimal keeps a clean line at the bottom, and bolder styles such as outline and neon suit rap and pop. Behind the text, scenes can follow the story of the song, stay abstract, or lean on cinematic B-roll.
Most artists need something on YouTube the day a single drops, long before a full music video is shot. A lyric video fills that slot, and the vertical cut of the chorus works as the teaser on TikTok and Reels. Both come from the same upload, so the words and the look stay the same everywhere the song is posted.
Text on a plain background is the cheapest lyric video, and it looks like one. Here each scene is a generated video clip directed from the line being sung: a lyric about leaving home gets a road at dusk, a lyric about a crowded room gets one. The camera language, pacing and genre notes you give shape every clip, so a drill track and an acoustic ballad come out looking nothing alike.
The karaoke highlight style lights up each word at the moment it is sung, which is what most people picture when they think of a sing-along lyric video. It works best on vertical clips where viewers often watch muted and read along. On 16:9 uploads, a minimal style at the bottom of the frame keeps the visuals in focus while the words stay readable.
Automatic transcription is fast, but a whispered ad-lib or a stacked harmony can come out wrong. Open the finished video in Studio, click the caption, type the right word and re-render. Your timing stays the same and you avoid redoing the whole video for one line, which matters when you are posting the same song in two formats.
The lyrics are taken from the vocal so the timing matches the recording. If a word comes out wrong, you correct it in Studio after the render, which keeps the timing and fixes the text.
Creating an account is free and new accounts get trial credits. Lyric videos use credits because every scene is a generated video clip, and the cost is shown before you render.
Vertical lyric videos run from 15 seconds to 3 minutes, which fits a chorus or a full radio edit. The 16:9 version runs up to 10 minutes for full songs on YouTube.
The transcription handles many languages, so lyrics in Spanish, Portuguese, Hindi and other languages are captioned in their own script. Check the captions after the render, as with any language.
Yes. Use your own music, music you have licensed, or royalty-free tracks. Uploading a lyric video for someone else's song can get it muted or claimed by the platform.
Both use the same format. A lyric video puts the words front and center with lyric-led scenes. The music visualizer leans on a waveform overlay and beat-synced motion, often with abstract scenes, for tracks where the sound matters more than the words.