Vertano
IN THE MATTER OF: YOUR UNREAD AUDIOCASE NO. ∞ VOICE MEMOSFILED: LOCALLY, ALWAYS
The exhibits

A stenographer that lives on your machine.

Cloud services charge by the minute and read your audio on their servers. Vertano does the same work locally, for nothing. Here is the full case.

Exhibit A: Private

Nothing leaves your machine

Your audio and transcripts are processed and stored locally, every time. Airplane mode works just fine.

Exhibit B: Batch

Folders, not files

Point it at a year of voice memos. Vertano queues everything, works through the list, and skips duplicates automatically.

Exhibit C: اردو

Urdu → English, built in

First-class Urdu support with one-tap translation to English, or keep the original script. 100 languages in total.

Exhibit D: Formats

Any audio you have

wav, mp3, m4a, flac, opus, voice memos, even the audio from your videos.

Exhibit E: Free

$0, no strings

Open source. No account, no trial, no meter. The speech model downloads once and is yours to keep, in whichever size you choose.

Exhibit F: Fast

Hardware-accelerated

Batches that would cost hours of upload time finish while you make tea.

Exhibit G: Captions

YouTube captions, cleaned

Auto-generated captions download with every line doubled. Drop the .srt or .vtt on Vertano and get a clean, correctly timed track, plus translated versions ready to re-upload.

Exhibit H: Models

Pick your power

Three recommended models — Efficient, Enhanced, Maximum — or open the full catalog of 20+ Whisper models, from tiny to large-v3, including English-only and compressed builds.

Exhibit I: Multilingual

One recording, many languages

Check as many target languages as you like. Every transcript is saved once per language, translated on your device by Apple's language packs.

Exhibit J: Findable

Recordings name themselves

Live recordings are saved under their opening words — “Meeting Q3 budget review.wav” — so a folder of transcripts is browsable at a glance, not a wall of timestamps.

Exhibit K: Live count

Word count as you speak

A running word count sits under the live transcript while you record, so writers and researchers can see how much they have captured at a glance.

Exhibit L: Searchable

Find any file in the queue

Point Vertano at hundreds of recordings and a filter box keeps the list navigable — type a few letters and the queue narrows to matching file names instantly.

Exhibit M: Streaming

Real-time live transcription

Live recording now streams: a rolling buffer is re-read every second and words lock in only once two passes agree, so text appears fast, firms up as you speak, and never breaks a word at a chunk edge.

Exhibit N: Progress

See the batch at a glance

A live progress readout in the toolbar shows how many files are done out of the total, and flags any failures, so a long queue never leaves you guessing.

Exhibit O: At a glance

Word count and reading time

While you record, a live readout shows the running word count and an estimated reading time, so writers and researchers know exactly how much they have captured.

Exhibit P: Long-form

Built for hour-long sessions

Record lectures, meetings, and interviews without watching the clock: the timer counts in hours, minutes, and seconds so multi-hour sessions always read correctly.

Exhibit Q: Resilient

Retry failed files in one click

If a file trips up mid-batch, it is flagged rather than lost. One Retry Failed button re-queues everything that failed, so a transient hiccup never means re-adding files by hand.

Exhibit R: Pace

Know your speaking rate

While you record, a live words-per-minute readout shows your pace — handy for presenters, podcasters, and interviewers who want to stay in a comfortable range.

Exhibit S: Cleaner

No more repetition loops

Whisper sometimes echoes a word over silence. Vertano quietly trims those runaway loops from the transcript while leaving everything you actually said untouched.

Exhibit T: Faster

Uses your whole machine

File transcription now runs across all your CPU cores with flash attention, instead of idling on a handful of threads, so a big batch finishes noticeably sooner — accuracy unchanged.

Exhibit U: Handy

Your recordings, one click away

An Open Recordings Folder button jumps straight to where your recordings and transcripts are saved, so you never have to hunt through Finder for them.

Exhibit V: Tidy

No [Music] clutter

Transcripts of videos and music-heavy audio come out clean: standalone sound-effect tags like [Music] and (applause) are stripped automatically, while notes like [inaudible] and everything spoken are kept.

Exhibit W: Loop-free

No runaway repeats

When a model stumbles on silence and echoes the same line over and over, Vertano folds those loops back to a single line, so long recordings do not end with a wall of duplicated text.

Exhibit X: Sized

Length at a glance

Every finished transcript shows its word count and estimated reading time, so you can size up a batch of files without opening a single one.

Exhibit Y: Totals

Your whole corpus, counted

The toolbar keeps a running total of every word transcribed across the batch, so researchers and writers can see the size of a whole project at a glance.

Exhibit Z: One grab

Copy the whole batch

Copy All puts every finished transcript on your clipboard at once, each under its file name, so a folder of interviews lands in your document in a single paste.

Exhibit AA: In control

Tidy the queue

Added the wrong file, or done with a result? Remove any single job with one click — no need to clear everything and start over.

Exhibit AB: Pause

Pause a big batch

Need your machine back for a moment? Pause processing and the current file finishes before Vertano stops; resume whenever you are ready, right where it left off.

Exhibit AC: Search

Find what was said

The filter box searches inside transcripts, not just file names — type a phrase and Vertano surfaces every recording that mentions it, turning a folder of interviews into a searchable archive.

Exhibit AD: Context

See the match in context

Search results show a short excerpt around each hit, right in the list, so you can spot the right recording at a glance without opening a single file.

Exhibit AE: Ranked

See who says it most

Each search result shows how many times your term appears in that recording, so the files that dwell on a topic stand out immediately.

Exhibit AF: Overview

The whole picture

Search a term and the bar tells you the totals at once — how many times it comes up and across how many files — so you can gauge a topic's reach over an entire archive.

Exhibit AG: Extract

Search, then grab the set

Filter to a topic and Copy Matching puts just those transcripts on your clipboard, headed by the search term — pull every mention of a subject into one document in a single step.

Exhibit AH: Archive

Save the set to a file

One Save writes the shown transcripts to a text file, named after your search, so a themed selection becomes a tidy document you can keep, share, or hand off.

Exhibit AI: Highlight

Matches, lit up

Open a search result and every occurrence of your term is highlighted right in the transcript, so you can jump to the moment it was said without reading the whole thing.

Exhibit AJ: Subtitles

Subtitles, for free

Every audio file you transcribe also gets timed .srt and .vtt subtitle files beside its transcript — SRT for video editors, WebVTT for the web and YouTube — ready to drop straight onto a video with no extra step.

Exhibit AK: Readable

Captions sized right

Long lines are wrapped to a comfortable caption length instead of dumping a whole sentence on screen at once, so the subtitles are watchable straight out of the box.

Exhibit AL: Your call

Subtitles on your terms

Want just the transcript? A single setting turns the subtitle files off, so you get exactly the outputs you need and nothing you don't.

Exhibit AM: Readable

Prose, not fragments

Flip one setting and transcripts save as flowing paragraphs instead of a line per segment, so they read like a document you can hand off — no reformatting.