← All models · MMS forced alignment
use case · basics
The fundamental output of forced alignment: a list of words, each with a start and end time. Align the bundled JFK clip, then click any word to jump the audio to the exact moment it's spoken.
CC-BY-NC-4.0 — non-commercial weights. For personal/educational use; see the main page for full license + attribution.
Bundled JFK sample: inaugural address excerpt (20 January 1961), spoken by John F. Kennedy — public domain, U.S. government work. JFK audio source and attribution record.
word timestamps — click to hear
Notice the timestamps are monotonic and land on the actual words — that's the aligner matching your transcript to the audio frames, not transcribing. Head to Practical to turn this into subtitles, or Wild to align your own voice.