WORDS THAT FOLLOW THE AUDIO
Subtitle generator. Ready to review.
Generate timed text with WhisperX, correct the words, and download SRT or VTT for your video editor.
WhisperX powered · Independent, unofficial service
Quick start
Play it. Change a word. Make it yours.
Result details & original output
THREE SIMPLE STEPS
How subtitle generator works
Upload the audio or video you want to caption.
Run WhisperX and review the transcript.
Download SRT or VTT, then check it in your destination player.
Pick the format your player accepts
SRT is a common import format for video editors. VTT is suitable for web players that use caption tracks. Both describe timed text; neither is a video file. Keep a TXT copy when you also need the script for review or publication.
ORIGINAL VTT CUE
WEBVTT
00:00:00.051 --> 00:00:02.315
Welcome to this WhisperX example.Correct the text before final delivery
Check spelling, speaker names, punctuation, and sentences cut by pauses. A change to a sentence keeps its segment timing but does not measure new word timestamps. If you substantially rewrite speech, review the timing against the recording.
Check captions in the final player
After exporting, import the subtitle file alongside the exact video you uploaded. Check the first cue, a cue near the middle, and the last cue. If your video editor changes the cut or adds an intro, the subtitle file needs a matching timeline adjustment.
Understand how alignment changes the output ↗CHECK THE OUTPUT YOURSELF
A recording. A transcript. A caption file.
This demonstration uses a synthetic recording and actual WhisperX processing. Download the source and the original result to check what the engine returned.
Quick start · Original model result
Original demonstration script; eSpeak NG synthetic voice; actual WhisperX large-v3 output.
Model: large-v3 · Provider: replicate
Pinned runtime version
655845d6190ef70573c669245f245892cd039df4b880a1e3a65852c09252f5ccTRANSCRIPT EXCERPT
0.05sWelcome to this WhisperX example.
2.73sUpload your audio, review the words as you listen, and download a transcript or subtitles.
8.64sYou do not need to install software or set up a graphics card.
Original output is separate from edits made in the interactive sample. Word times may include estimated positions; check them before precise timing work.
BEFORE YOU START
Prepare the file. Know what you will get.
Supported recordings and limits
Upload MP3, WAV, M4A, FLAC, OGG, MP4, MOV, or WebM. This hosted release supports English speech. Use a file you have permission to process; external links and live recording are not supported.
The one-time trial includes 5 processing minutes, with files up to 100 MB and 5 minutes long. Paid accounts support up to 500 MB and 60 minutes per file. Confirm the measured duration before starting; a failed task releases its reserved minutes. See the minute packs.
Choose the right next step
For a written draft from an audio recording, use audio to text. To review speech beside its original video, use video to text. For interview turns and participant labels, explore speaker diarization.
All workflows use the same WhisperX engine and account. Your results are private, with 7-day trial retention and 30-day paid retention. Download what you need to keep. Read the workflow guide and recording privacy information before your first upload.
GOOD TO KNOW
Subtitle generator questions
Are subtitles translated into another language?
No. The current output is a transcript of the original speech. Translation is a separate task and is not included.
Can I upload an existing script and align it?
The current service starts from audio or video and produces a transcript. Uploading an existing script for alignment and automatic realignment after edits are planned separately.
Do exports cost more minutes?
No. Editing and downloading TXT, JSON, SRT, or VTT from an existing result do not run another transcription or add a processing charge.
LESS SETUP. MORE DONE.
Your next transcript starts here.
Try the public sample, then bring your own recording. Your first account includes 5 minutes to try the workflow.
Run WhisperX