Docs/Workflows/lyrics-to-video

Lyrics to music video

Revid generates an original song from your lyrics (or writes the lyrics from a description), then a music video synced to it.

Requiressource.text (the lyrics) or source.prompt (a description of the song)alias: text-to-music-videoalias: song-to-video

media: ai-videovoice-over: off by defaultmusic: on by defaultcaptions: on by defaultratio: 9:16 by default

Build your request

Only the parameters that apply to lyrics-to-video are shown. Set values on the left, copy the payload on the right.

View as Markdown (for LLMs)

source.text

The exact script to be spoken. For script-to-video it can also be an X/Twitter or LinkedIn post URL: the post content becomes the script. For lyrics-to-video and song-ad, the lyrics, sung as written ([verse], [chorus] sections supported).

source.prompt

What the video should be about: the AI writes the script. For music-to-video it is an optional creative brief for the visual storyline. For lyrics-to-video, a description of the song to write (10 to 500 characters). For song-ad, the ad to write: the product or its page, the audience and the outcome. For character-swap, optional instructions on top of the swap (an outfit, ...).

{
  "workflow": "lyrics-to-video",
  "source": {
    "prompt": "An upbeat pop song about shipping a side project at 3am"
  }
}

Free, no API key needed.

Good to know

→Runs the same tool as the Lyrics to Music Video form on /create: the song is generated with vocals, then the video is cut to it.
→source.text is sung as written (up to 5,000 characters, sections like [verse] and [chorus] are supported). source.prompt (10 to 500 characters) describes the song instead, and Revid writes the lyrics. Pass one of the two, not both.
→music.generationMusicPrompt sets the style of the song (genre, mood, voice), for example "upbeat synth pop, female vocal".
→music.syncWith lyrics (default) shows the lyrics as captions; beats cuts on the beat without lyric captions. music.soundWave adds a sound wave.
→music.enableLyricsLipSync + music.lipSyncFrequency have characters sing the lyrics on camera; options.speakerCount (auto, 1 or 2) caps the singers detected for lip sync.
→media.provided images (artist, a place, an object) are kept as they are in the scenes that show them. characterIds use saved consistent characters.
→options.promptTargetDuration ("auto" or seconds) sizes the song written from source.prompt.

Music to video All workflows Song ad