Speech to text

Video transcription thatdrives the whole edit

Shorz transcribes your footage before it edits it — and then every other feature reads that transcript. Captions, clip selection, B-roll placement, titles and sound effects all come from the same source of truth.

A video being converted into a timed text transcript in Shorz

How to use the video transcription in three steps

A transcript isn't a deliverable in Shorz — it's the input the rest of the app runs on. It's how captions land on the syllable, how Clipping knows which sixty seconds of a podcast are worth cutting, how B-roll knows what's being talked about, and how Auto SoundFX knows where a sound belongs.

Selecting a local video file to transcribe in Shorz
1

Point it at a video

Any local video file with speech. Long footage takes a few minutes; Shorz runs it in the background while you keep working on the project.

Any local file

A timed transcript with per-word timestamps shown next to a video
2

Get timed text back

Not a wall of text — a timed transcript. Every word carries a timestamp, which is what makes word-level captions and precise clip boundaries possible.

Timestamps, not just words

A transcript feeding captions, clip selection and B-roll placement in Shorz
3

Let the rest of the app use it

Captions, highlight detection for clipping, B-roll placement, AI title generation and Auto SoundFX all read the same transcript. Transcribe once, and the whole edit gets smarter.

One transcript, six features

Find it in the app under Auto Edit & Clipping → transcription pass · MCP single-file tool.

Why Video Transcription in Shorz

The Shorz clipping workspace selecting highlights from a long video

How Clipping finds the good bits

Clipping reads the transcript and the screen to rank the moments most likely to land, then cuts up to 8 vertical clips from one long video. Without a timed transcript that's guesswork; with it, it's selection.

Powers highlight detection

A cost badge showing roughly one credit per minute of transcription

Cheap, and usually already included

Transcription runs around 1 credit per minute on its own — about a cent. Inside an Auto Edit or Clipping run it's part of the pass, including on the free weekly allowance.

~€0.01 per minute

Who uses it, and for what

Finding highlights: Know which sixty seconds are worth clipping.

Finding highlights

Know which sixty seconds are worth clipping.

Caption source: Word-accurate subtitles with no typing.

Caption source

Word-accurate subtitles with no typing.

Show notes: Turn an episode into text you can repurpose.

Show notes

Turn an episode into text you can repurpose.

Searchable footage: Find the moment someone said the thing.

Searchable footage

Find the moment someone said the thing.

Shorz speaks MCP

Shorz isn't a locked web app. Connect it to Claude, Cursor, Codex or Gemini and your assistant can drive it directly — one message instead of a panel full of clicks. You review before anything is published.

See how MCP automation works
An AI assistant asks Shorz: Transcribe this recording, find every mention of pricing, and cut a clip around each one.

You say

“Transcribe this recording, find every mention of pricing, and cut a clip around each one.”

Shorz does

  • 1Transcribe the file
  • 2Search the transcript for the topic
  • 3Trim a clip per match
  • 4Save them to the library

Every tool ships with the same promises

They're not separate products with separate bills. One app, one credit balance, one export that belongs to you.

  • No subscription — prepaid credits that never expire
  • No watermark on anything you export, ever
  • Full commercial rights on what you create
  • A desktop app for Windows and Mac — your files stay on your machine
  • Auto Edit and Clipping: 4 free videos a week, no card
  • Drivable from Claude, Cursor, Codex or Gemini over MCP

Video Transcription questions

It depends on the length of the footage — long videos can take a few minutes. It runs in the background, so you can keep setting up the project while it works.

Roughly 1 credit per minute of video, so about a cent a minute (1 credit = €0.01). Inside an Auto Edit or Clipping run it's part of the pass — including on the free weekly allowance.

Word-level subtitles, highlight detection for Clipping, B-roll placement, AI title generation and Auto SoundFX placement all read it. One transcription makes the whole edit smarter.

Yes. Transcription is one of the tools exposed over MCP, so Claude, Cursor, Codex or Gemini can transcribe a file and act on the result — for example, finding a quote and cutting a clip around it.

Still have questions? Ask founder