Skip to main content
Every transcription job runs in one of three modes, selected by combining the align and review parameters. The mode determines what output is produced, how long it takes, and how results are delivered.

​
Mode comparison

ModeParametersOutputApprox. timeBest for
Transcript onlyalign=falseTranscript + transliteration + translation + cultural notes~60sMetadata, liner notes, sync licensing
Full pipelinealign=true (default)All of above + LRC + SRT + word-level JSON~90sKaraoke, lyric display, DSP delivery
Reviewed deliveryalign=true + review=trueAll of above, delivered after artist approval~90s + reviewArtist approval workflows

​
Mode 1 — Transcript only

Set align=false to skip time-alignment entirely. lyrcs.ai transcribes the audio and returns the lyrics as structured text. No LRC or SRT files are generated. 
{
  "audio_url": "https://cdn.example.com/song.mp3",
  "language": "Hindi",
  "align": false
}
Output fields:
  • results.transcript — lyrics in the original script
  • results.transliteration — phonetic romanisation
  • results.translation — English translation
  • results.cultural_notes — contextual notes (may be null)
What’s missing: results.downloads is not present. No LRC or SRT files. Use cases:
  • Delivering lyric metadata to streaming stores (Spotify, Apple Music, Amazon)
  • Generating liner notes for releases
  • Populating sync licensing databases with searchable lyrics
  • Any workflow where timing is not needed

​
Mode 2 — Full pipeline

The default. Transcription runs first, then alignment maps each lyric line to a timestamp in the audio. 
{
  "audio_url": "https://cdn.example.com/song.mp3",
  "language": "Tamil"
}
Output fields:
  • Everything from Mode 1, plus:
  • results.downloads.lrc_original — time-synced LRC in original script
  • results.downloads.lrc_transliterated — time-synced LRC in romanised form
  • results.downloads.srt_original — SRT in original script
  • results.downloads.srt_transliterated — SRT in romanised form
  • results.downloads.words_original — per-word timestamps in original script (JSON)
  • results.downloads.words_transliterated — per-word timestamps in romanised form (JSON)
Word-level JSON is included by default with all aligned jobs (word_align=true). Set word_align=false to skip it and receive only LRC and SRT. Use cases:
  • Karaoke and sing-along applications
  • Lyric display synced to audio playback on streaming platforms
  • Subtitle tracks for music videos
  • Live lyric scrolling on DSPs

​
Mode 3 — Reviewed delivery

Adds an artist approval gate. After alignment completes, results are held and a job.awaiting_review webhook fires with a review_url. The job.complete webhook fires — with full results — only after the artist approves. 
{
  "audio_url": "https://cdn.example.com/song.mp3",
  "language": "Punjabi",
  "review": true,
  "webhook_url": "https://api.example.com/webhooks/lyrcs"
}
Delivery sequence:
  1. Transcription + alignment completes (~90s)
  2. job.awaiting_review fires → contains review_url
  3. Distributor forwards review_url to artist
  4. Artist approves in lyrcs.ai Studio
  5. job.complete fires → full results + downloads
Use cases:
  • Artist approval required before public lyric delivery
  • Quality control for high-profile releases
  • Markets where lyrics are legally sensitive and must be approved by rights holders

​
Decision guide

Do you need time-synced lyrics (LRC/SRT)?
├── No  → align=false (Mode 1, ~60s, faster)
└── Yes → Does the artist need to approve before delivery?
           ├── No  → align=true (Mode 2, default, ~90s)
           └── Yes → align=true + review=true (Mode 3, ~90s + review time)
review=true requires a webhook_url to be useful — without it, there’s no way to receive the review_url and no way to know when approval happens.