Speech Detection

Sighthound Redactor can transcribe the audio in a video so that specific words, phrases, and entire speaker turns can be found and redacted. Once a video has been transcribed you can search the transcript, seek to any word in the video player, and redact words either individually or everywhere they occur. Redactor also detects who spoke when (speaker diarization), so you can redact everything a single person said in one action.

Supported Languages

English ships with Redactor and is ready to use straight away. When your organization enables it, the following additional languages can be downloaded on demand the first time you select them (see Downloading a Language):

  • Czech
  • Dutch
  • French
  • German
  • Italian
  • Polish
  • Portuguese
  • Russian
  • Spanish

Chinese, Japanese, and Korean can be transcribed but use timing-only alignment — there is no word-level alignment model for these writing systems — so they are not offered in the editor's language picker.

Transcribing Videos

The Speech button can be found in the bottom right of the video editor screen. Once clicked it will open the speech detection panel on the right. Select a language from the picker and a "transcribing speech" screen will appear with a loading bar. You can wait until it's done processing, or click Run in background if there are other projects you'd like to look at. When it is done transcribing you can search, seek to, and redact words — and work with the speakers Redactor detected.

If you pick a language that hasn't been downloaded yet, Redactor will offer to download it first.

Downloading a Language

The first time you choose a language that isn't already installed, Redactor shows a confirmation dialog with the approximate download size. Confirm, and the language model is fetched in the background while a progress indicator keeps you informed. You can cancel the download at any time; if you do, nothing is left behind and you can try again later.

Downloaded languages persist — they stay available for future videos and survive application updates and reinstalls, so each language only needs to be downloaded once. Only one language downloads at a time.

Searching & Seeking Words

Use the search bar at the top of the panel to find a specific word/words used throughout the video. Once you search, the panel will display every instance when the word or partial word was used, along with a timestamp of where it is in the video and the words right before and after it. You can also click on the word and the video player will seek to that point in the video.

Redacting Words

You can redact words either by scrolling through the transcript or by searching for a specific word. Right-click the word you want to redact to open the transcription menu, which offers:

  • Redact the single word you clicked — the menu item is labelled with the word itself, in quotes (for example, Redact "license").
  • Redact every phrase — redact every occurrence of that word or phrase throughout the video.

Redacting mutes the matching span of audio; the redacted word is highlighted in the transcript and a muted region appears on the audio timeline. To reverse a redaction, right-click a redacted word and choose the matching Unredact item.

Redacting a Selection of Words

To act on several specific words at once, drag to select two or more words in the transcript and then right-click the selection. The single-word items are replaced by selection-aware items:

  • Redact words — redact every word in the selection.
  • Unredact words — remove the redactions from every word in the selection.

If your selection contains a mix of redacted and un-redacted words, both items are offered so you can apply whichever you need. Selected redacted words are shown with a distinct highlight, and adjacent selected redacted words read as one continuous band.

All of these actions can be reversed with Ctrl+Z from inside the panel.

Speakers

When a video is transcribed, Redactor also performs speaker diarization — it works out who spoke when and groups the words by speaker. Speakers are numbered in the order they first appear (Speaker #1, Speaker #2, and so on), and each word is given a thin underline in a color unique to its speaker, so you can see at a glance how a conversation moves between people. The underline sits beneath the text and never interferes with the redaction highlight.

Redacting by Speaker

Diarization lets you redact everything a person said without picking through the transcript word by word. Right-click any word that belongs to a speaker and choose:

  • Redact speaker #N — mute every word spoken by that speaker.
  • Unredact speaker #N — remove those redactions again.

When you redact a speaker, consecutive words from that speaker — including the short pauses between them — are merged into a single continuous muted region, so the speaker's turn plays back as one uninterrupted silence instead of a string of choppy micro-gaps. Unredacting removes exactly the same region, leaving nothing behind.

Reassigning & Creating Speakers

Automatic diarization is highly accurate, but occasionally a word or run of words is attributed to the wrong speaker — or you may simply want to give a speaker a meaningful name, such as "Officer" or "Witness". Select the word or words in question, right-click, and choose Reassign Speaker to open the reassignment dialog.

Start typing in the box and the list of existing speakers is filtered as you type. From there you can either:

  • Choose an existing speaker — the selected words are reassigned to that speaker.
  • Type a new name — a new, named speaker is created and the selected words are assigned to it.

Speaker names follow a few simple rules:

  • They cannot contain the characters (, ), or !.
  • Leading and trailing spaces are removed automatically.
  • They can be at most 64 characters long.
  • They must be unique — a name that already belongs to another speaker cannot be reused (matching ignores upper/lower case).

Reassigning or creating a speaker updates the colored underlines throughout the transcript, and can be undone with Ctrl+Z.