Timestamped Lyrics Synced to Your Music

Pick a track that already lives in your Music Factory library and its words come back carrying their own timings. The studio writes them out as timed lines and puts Copy and Download .lrc beside them — LRC being the standard format that karaoke systems and media players use to scroll and highlight words in time with the audio. You choose that source track in the studio — nothing is uploaded, so the tool only ever reads a recording you pointed it at.

LRC is a plain-text format for time-synced lyrics. Every line starts with a timestamp in [mm:ss.xx] brackets — minutes, seconds, and hundredths of a second — followed by the words sung at that moment. For example, a line might read [00:12.40]Every night I dream of you. Any media player, karaoke app, or subtitle tool that understands LRC will read those brackets and highlight or scroll each line exactly when it plays, so you do not have to align anything by hand.

This is one of the few Music Factory features that runs synchronously. Instead of starting a background job and waiting for a callback, the run is already finished when it returns and the timed words are on the card. It can do this because the track already exists rather than being generated — there are no frames to render and no vocals to synthesise, so there is nothing to wait on.

Most Music Factory tools create new audio and run asynchronously; Timestamped Lyrics works from a track that already exists and returns text, instantly. The table below shows where it sits relative to the tools people usually pair it with — you would typically generate a song with Generate Music, optionally strip the backing with Vocal Separator, then run Timestamped Lyrics to get the synced words: Feature · Output · Speed · Credits — Timestamped Lyrics · LRC synced text · Instant (synchronous) · 20 — Generate Music · 2 audio tracks · Background job · 20 — Vocal Separator · Vocal + instrumental stems · Background job · 30 — Music Video · MP4 video · Background job · 20

Yes. LRC line timestamps convert cleanly into SRT or VTT — the two subtitle formats every video editor understands — so you can drop your song's lyrics onto a music video or a lyric video as captions that appear exactly on beat. Because each LRC line already carries its own start time, you are only mapping one timing scheme to another rather than nudging captions around by ear, which is the tedious part of subtitling audio by hand.

Pair Timestamped Lyrics with the instrumental stem from Vocal Separator: play the instrumental as the backing track and feed the LRC into any karaoke or lyric-scroll player. As the instrumental plays, the player uses the LRC timestamps to highlight each line right as the singer would hit it. That combination — an instrumental bed plus synced words — is the whole recipe for a karaoke version of a song you generated in Music Factory.

Timestamps are placed to the hundredth of a second per line, which is the resolution LRC itself supports. Line-level timing is more than precise enough for karaoke scrolling and lyric videos. If a particular line ever looks early or late in your player, you can nudge that single timestamp by editing the plain-text LRC.

Run it on a track from your Music Factory library that was sung — the picker lists nothing else, so there is no upload to prepare. Instrumental-only tracks have no lyrics to time-stamp, so they are not suitable input.

Each extraction costs 20 credits, with plans starting at $19.99 and credits included. You can run it on any eligible track in your library, and you can re-run it if you want a fresh copy of the LRC. Because the output is a small text file rather than rendered media, extractions are quick and inexpensive relative to audio or video generation, which makes it practical to time-stamp a whole set of tracks before publishing.

Yes, and it is easy because LRC is plain text. Open the file in any text editor and you will see one line per lyric, each led by a bracketed timestamp. To fix a typo, edit the words after the bracket; to shift a line earlier or later, change the numbers inside the bracket. This means you are never locked into the exact output — if you want a line to appear a beat sooner on your karaoke display, you nudge one timestamp by a few hundredths of a second rather than regenerating the whole file. Keeping the format human-readable is one of the reasons LRC has stayed the standard for synced lyrics.

Run the extraction on each track one at a time, saving each LRC alongside its audio. Because the feature is synchronous and returns a small text file, you can move through a set of tracks quickly without waiting on background jobs between them. A common workflow for a release is to generate every song first with Generate Music, review and finalise them, and only then time-stamp the whole set in one sitting so that every track ships with its synced lyrics ready for lyric videos, a karaoke build, or an in-app player.

The run carries the track you picked and nothing else — there is no language setting to choose and no lyrics for you to supply, because the words come back with the track. What it needs is a song that was sung: an instrumental-only track has nothing to stamp.