Generate subtitles from any video or audio

How the subtitle generator works

Drop a video or audio file and Hushscript’s subtitle generator transcribes the audio, separates the speakers, and times every line automatically. Compatible audio uploads unchanged. For video, a compatible audio track is copied in the browser without re-encoding, and local conversion runs only when required, so the video itself never uploads. Recordings can run up to 10 hours, with no file-size limit — large video and audio are prepared right in the browser. Preview the first 30 seconds free, with no account needed; sign up to transcribe the rest and unlock export. From there, fix a line, rename a speaker, and download captions in whatever format your editor or player expects.

Every subtitle format your workflow needs

Subtitle exports aren’t a separate product. They come out of the same transcript, in any of the 21 formats it can produce, at no extra charge. Guess the wrong format and a caption file that looks perfect in a text editor can fail to import; pick the one your player or editor actually expects:

Format	Best for
SRT	The default; works almost everywhere
VTT	Web players (HTML5 <track>)
ASS	Styled captions with fonts, colors, positioning
TTML	Broadcast and streaming platforms
SBV	Older players that still expect it
LRC	Lyric-sync and music apps
FCPXML	Timeline markers for Final Cut
EDL	Timeline markers for Premiere, Resolve, and other NLEs

Every format above is included with transcription; there’s no subtitle add-on to buy separately. Looking for a video to SRT converter or an SRT generator? This is that tool: upload, transcribe, and export as SRT, or any of the other seven. Already have a subtitle file and just need to swap formats instead of transcribing? The free, browser-based subtitle converter handles that without an upload.

Speaker-labeled captions

Captions come back with the speaker already attributed, free on every transcript, not a paid add-on most tools gate behind a higher tier. A two-person interview reads as two clearly separated voices instead of one run-on block, and multi-speaker meetings stay readable instead of turning into a wall of text. Rename “Speaker 1” to a real name in a click, and every exported caption file updates to match.

Edit, then export

Fix a misheard word, tighten a line that’s too long for the screen, or swap a name before you download. The transcript editor supports find/replace and per-line edits, so a mistake in the transcript doesn’t ride along into your captions untouched. Export only once the text reads the way you want. If you catch something later, edit again and re-export; nothing about the caption files is locked after the first download.

Subtitles in other languages

Need the captions in a language other than the one spoken in the recording? Translation is a paid add-on, priced at roughly a quarter of the transcript’s length per target language, selected before you start. The translated captions keep the same timing and speaker labels as the original, so they drop onto the video the same way. If you only need the words in the language actually spoken, that’s the plain subtitle generator described above, with no translation and no add-on.