ZumiScribe Open ZumiScribe

A ZumiLabs experiment

Every conversation, captured your way.

Record live or transcribe later. Capture meetings, calls, presentations and recordings. Identify speakers, generate summaries and stay in control of your data.

Transcripts that know who said what.

Try ZumiScribe Free Watch Demo

In-person meeting Works in the browser

Everyone in the room, one microphone, every voice named.

Put a laptop on the table and press Record. Leave with a summary, the decisions and the action items.

  • Attendees from a pasted invite or a screenshot of the call
  • Fix a voice afterwards: review each one, play a few bubbles, rename or reassign
  • Summaries written on your own computer
Try it free

Online meeting Works in the browser Single-app sound needs the ZumiScribe Local app

Zoom, Teams, Meet: you and the others, labelled.

Capture the meeting from a browser tab or the screen, with your microphone mixed in, and names appear as people speak.

  • Tab or screen sound, or one app with the ZumiScribe Local app
  • Pictures of shared slides land on the bubble they appeared with
  • Notes and bookmarks while you listen
Try it free

Phone call Works in the browser

Two people, on speaker, both sides labelled.

Choose Phone call and ZumiScribe sets itself up for two voices: no attendee list, no fuss.

  • Listens through your microphone while the call is on speaker
  • Each person gets a colour, and you name them with one click
  • Search, summarise and export afterwards
Try it free

Conference presenter Phones need the ZumiScribe Local app

You speak: captions for the audience.

Large captions on the big screen, and the audience can follow on their own phones. Nothing to install on the phones.

  • Large captions readable from the back of the room, coloured by speaker
  • Translate the captions into another language, on your computer
  • A see-through subtitles window over your slides (ZumiScribe Local app)
Try it free

Conference attendee Works in the browser

You listen: notes and slide pictures.

Let ZumiScribe write down the talk while you think. A picture of each new slide lands beside the words said with it.

  • Automatic snapshots when a new slide appears, kept with the words
  • A Notes panel for your own thoughts, and bookmarks for the moments to come back to
  • A summary and action items when it ends
Try it free

Student at a lecture Free, and can stay on your device

Never miss what was said.

Listen now, learn from the whole lecture later. Photos of the board land beside the words said when you took them, and one document pulls the lot together for revision.

  • Photos from your phone sit on the moment they were taken, even if its clock was out
  • A study summary: key ideas, definitions, examples and questions to test yourself
  • Export a PDF or Word document with the pictures in place, and ask across a whole course
Try it free

Subtitle a video Works in the browser

Subtitle a recording as it plays.

Play a recording as if it were live, hear it while you read along, and fix the words as they appear.

  • Transcribe a whole file in seconds with a fast engine, or play it live
  • Correct any word with a click, and rename the speakers
  • Export SRT or WebVTT subtitles, or a Word or PDF document
Try it free

See it in 90 seconds

Who said what, the slide on screen when they said it, and nothing leaving your computer.

A narrated tour of the app, 1 minute 30 seconds, with captions. The voice is synthetic.

Works offline

No network, no problem.

Download a speech engine once, then unplug. ZumiScribe goes on recording and transcribing on your own computer: on a plane, in a basement meeting room, or anywhere the wifi cannot be trusted.

Try it free How offline works

  • Download once. Voz + Who is about 450 MB and Granite about 320 MB, kept by your browser. After the first visit the page itself is kept too, so it opens with no connection.
  • Then everything runs on your device. Words appear as people speak, with no audio leaving the computer. Voices are labelled too: live with Granite or the ZumiScribe Local app, and afterwards with Voz + Who.
  • Summaries and translation can stay offline. Write summaries with Ollama or Chrome's built-in AI, and translate with a language you have already downloaded.
  • Cloud services need a connection. Settings shows which transcribers stay on your device and which do not, so you know before you leave the office.

More than a transcript

The things you will not find in most meeting tools.

You decide where your data goes.

Pick a speech engine on your own device and your audio never leaves it. Pick a cloud service and it goes to that company, directly, with your own key. Either way there is no ZumiScribe server in the middle, and your recordings are ordinary files in a folder you choose.

The Transcriber settings table filtered to engines that stay on this device, showing which run in the browser and which on this Mac, what they report and what they cost
Every transcriber says where your audio goes. Filter to the ones that stay on this device.

Find the best transcriber for your audio.

Run one recording through several transcribers, from eleven cloud services to engines on your own computer, and see where they disagree, with the time each took and an estimate of the cost. Or queue a whole folder of recordings and walk away.

The compare dialog: three transcriptions of one recording side by side, the words that differ highlighted, with time taken, estimated cost and the share of words that differ
One recording, three transcribers, the differences marked. (Example results.)
The Batch tab: four recordings queued, one transcriber ticked, and a Run button
Or queue a whole folder and walk away.

Pictures, in context.

Slides are captured when the picture changes, and you choose the part of the screen to watch, so people, cameras and chat do not trigger a capture. Photos from your phone or camera land on the bubble being spoken when they were taken, even if the phone's clock was a few minutes out.

A transcript with a whiteboard photo and an action attached to the bubble that was being spoken
Photos and slides sit on the bubble being spoken.
A captured slide opened full size, with the window it came from named underneath
A captured slide, with where it came from.

Summaries you can trust with the room.

One button writes a summary, key points, decisions and action items, including the actions you noted along the way. Choose the shape: a one-to-one, an interview with verbatim quotes, a stand-up, a formal meeting with resolutions, or a follow-up email ready to send. By default the model runs on your own computer (Ollama or Chrome's built-in AI), so the words stay there. Then ask across everything you have saved, such as "what did we decide about the budget?", and get an answer with links back to the passages it came from.

  • General
  • 1-on-1
  • Interview
  • Stand-up
  • Board meeting
  • Lecture notes
  • Follow-up email
  • Your own prompt
The Library with a question typed into Ask your meetings, an answer with numbered citations, and the list of source passages from three saved meetings
Ask across everything you saved, with the sources listed. (Example meetings.)
The summary dialog in the Lecture / study notes format: summary, key ideas, definitions, examples, questions to review and a to-do, with the format menu below
A study summary of a lecture. (Example summary.)

One document, with the pictures where they belong.

Export a PDF or Word document with the transcript, the summary and every photo or slide sitting under the words that were said when it appeared. Choose what goes in: times, summary, pictures, attachments, and, if you want them, your own notes and actions. It is built on your computer and nothing is uploaded. Share it with the team, or print it and revise from it.

  • Transcript
  • Summary
  • Photos and slides
  • Attachments
  • Your notes and actions
An exported document: the lecture title, a summary at the top, then each speaker's words with a whiteboard photograph under the bubble it was taken at
The document: summary first, then the words, with the photo where it belongs. (Example lecture.)
The Make a document dialog with tick boxes for times, the summary, the pictures and attachments, and your private notes
You choose what goes in.

Built for the lecture hall.

Choose "Student at a lecture" and ZumiScribe sets itself up for one speaker, with the sound kept so you can listen again. Take notes as it goes, and bookmark the moments to come back to. Snap the board on your phone and the photo lands on the right moment, even if the phone's clock was out. Afterwards, a study summary gives you the key ideas, definitions and worked examples, with questions to test yourself, and Ask your meetings works across the whole course. Please check that you are allowed to record before you start.

  • Free to use
  • Can stay on your device
  • Photos synced to the words
  • Study summary
  • Ask across a course
  • Captions and translation
A lecture transcript with a bookmark, a whiteboard photo on its bubble, a note, and the Notes panel open beside the Voices panel
Bookmarks, a note, the whiteboard photo and your own Notes panel. (Example lecture.)
The Start a recording screen with eight recording types, Student at a lecture chosen
Choose Student at a lecture and it sets itself up.

Take it wherever it needs to go.

Export to Markdown with front matter that Obsidian and Logseq read as properties, plain text, subtitles (SRT and WebVTT) or JSON. Copy just the summary for an email or chat, or send the finished transcript to Slack, Teams, Zapier, Make or n8n when you stop recording. Your private notes stay out of every export, except a PDF or Word document where you choose to include them.

  • Markdown
  • Text
  • SRT
  • WebVTT
  • JSON
  • PDF
  • Word
  • Slack
  • Webhook
The Export menu: Markdown, plain text with and without times, SRT and WebVTT subtitles, JSON, a PDF or Word document with pictures, and Send to my web address
Every format, from one Export button.

A glossary that explains your jargon.

Abbreviations are underlined in the transcript. Click one to see what it means in your company's own glossary. Custom vocabulary teaches a tool how a word sounds; this explains what it means, and only the word you click is ever looked up.

A transcript with the abbreviation PXP underlined and a pop-up giving its meaning from the company glossary
Click an underlined abbreviation to see the company glossary definition. (Example glossary.)

Fix it while it is happening.

Click a word to correct it, give a sentence to someone else, split or merge bubbles, and play any bubble back. Afterwards, review each voice, check the likely mistakes, and let Who label the speakers from the sound.

The Review voices dialog: each voice listed with its bubbles, a Play button for each, and options to rename, give a bubble to someone else, or give the whole voice to someone
Review each voice, play its bubbles, and give them to the right person.
Two selected bubbles with a menu to merge them as one speaker, assign them to someone, or delete them
Select several bubbles, then right-click: merge, assign or delete. Ctrl or Cmd+J joins them.

Captions the whole room can read.

Switch to large captions for a big screen or a second monitor, with each speaker in their own colour. Share a link and people follow along on their own phones, with nothing to install.

Large captions: recent lines in the colour of each speaker above the line being spoken, at a very large size
Large, colour-coded captions, readable from the back of the room.
A phone showing live captions in a browser: the speaker's name, then large words with the last few still settling in grey italics, and buttons for Scroll, Live captions, History, Smooth and Confirmed only
Anyone can follow on their own phone, with nothing to install. (Example lecture.)

Subtitles on top of anything.

With the ZumiScribe Local app on a Mac, a see-through subtitles window floats over a film, a webinar or a call and captions whatever that app is playing, in large type you can read from across the room. It works offline with Voz + Who, so a video you have downloaded is captioned on a plane too.

A film frame with a subtitles window across the bottom: a control bar (Start, text size, background, names, settings) above two lines of large white captions, with the engine named as Voz + Who on this Mac
Subtitles over a film playing in a browser. Film: Sintel, © Blender Foundation | durian.blender.org, CC BY 3.0.
The audio source step with An app on this Mac chosen and a Which app menu listing Zoom, Microsoft Teams, Safari and Spotify
Choose which app to listen to.

How it works

  1. Record, or drop in a file

    Press Record in your browser, capture a call, or drop in an audio or video file, or a link to one. No installation.

    The Start a recording screen with seven recording types
  2. Voices get names and colours

    Words appear as people speak, each voice in its own colour. Name them from the attendee list, or fix them afterwards.

    A transcript with each speaker in their own colour and the Voices panel
  3. Edit, summarise, share

    Correct a word with a click, write a summary with action items, search every meeting, and export to Markdown, PDF or Word.

    The notes dialog listing bubble notes and an action with an owner and due date

Open ZumiScribe Try a sample recording first

Product highlights

A look inside, one screen at a time.

A transcript with each speaker in their own colour and the Voices panel
Every voice, named and colouredWords appear as people speak, each voice in its own colour, with a panel to name them.
A transcript with a whiteboard photo and an action attached to the bubble that was being spoken
Photos and slides, where they were saidA whiteboard photo or a captured slide sits on the bubble being spoken.
A lecture transcript with a bookmark, a whiteboard photo on its bubble, a note, and the Notes panel open
Built for lecturesBookmarks, notes, photos and a Notes panel of your own, beside the words.
Ask your meetings: a question, an answer with numbered citations and the list of sources
Ask across everything you savedAnswers cite the passages they came from. (Example meetings.)
The compare dialog: three transcriptions of one recording side by side with the differences marked
Compare transcribers on one recordingSee where they disagree, how long each took and what it cost. (Example results.)
The Batch tab with four recordings queued, one transcriber ticked and a Run button
A whole folder in one goAdd the recordings, tick the transcribers, press Run.
A transcript with the abbreviation PXP underlined and a pop-up giving its meaning from the company glossary
A glossary that explains your jargonClick an underlined abbreviation to see what it means. (Example glossary.)
A transcript where each bubble shows a Spanish translation as the large text with the English original smaller underneath, and the Translate button lit
Read it in your languageThe translation as the large text, the words as said underneath, translated on your device. (Example translation.)
Two selected bubbles with a menu to merge them as one speaker, assign them to someone, or delete them
Merge, assign or delete in a clickSelect several bubbles, then right-click. Or press Ctrl or Cmd+J to join them.
A film frame with a subtitles window across the bottom: a control bar above two lines of large white captions
Subtitles on top of anythingA see-through window over a film, a webinar or a call. Film: Sintel, © Blender Foundation, CC BY 3.0.
The Transcriber settings table filtered to engines that stay on this device
You decide where your data goesEvery transcriber says whether your audio stays on this device.
The transcriber table filtered to those that work on phones, with the Android Parakeet row marked as running
On phones tooCloud services work in a phone browser, and the Android app transcribes on the phone itself.
Large captions: recent lines in the colour of each speaker above the line being spoken, at a very large size
Captions the whole room can readLarge, colour-coded captions for a second screen, and a link for phones.

Everything in one place

Twenty transcribers behind one interface, a library that is just files in your folder, and tools for the awkward parts: wrong speaker labels, long recordings, no signal.

  • Choose your speech engine

    Eleven cloud services with your own key (most have a free trial), or models that run on your own computer. Change your mind any time.

  • Fix the speakers

    A Voices panel, a dialog that plays a few bubbles of each voice, a check that finds probable mistakes, and Who, which labels speakers from the sound.

  • Batch and compare

    Queue a folder of recordings, or run one through several transcribers and see how much they disagree.

  • Audio only

    Capture the sound when there is no signal or no credit, and transcribe it later, one file or a folder.

  • Notes that stay yours

    A rich-text Notes panel for the whole recording, notes and bookmarks on bubbles, pictures and files. All private.

  • Summaries and questions

    A summary, key points, decisions and action items from a model on your own computer, and Ask your meetings across everything you saved.

  • Captions for an audience

    Large captions in the speaker's colour, followed on phones with a link, and translated on your computer.

  • Search, replace, clean up

    Search by pattern, replace in bulk, auto-corrections, a glossary for abbreviations, and optional filler-word and swear-word clean-up.

Read the questions and answers

Your recordings stay yours.

ZumiScribe has no server of its own and no account. Recordings, transcripts and pictures are files on your computer, in a folder you choose.

  • Local engines send nothing anywhere. With Voz + Who, Granite or the Parakeet engine, your audio is turned into text on your own device.
  • Cloud services see your audio. If you pick one, the sound goes to that company while you record. It says so before you start.
  • Free to use. There is no subscription. Cloud services bill you directly, and most have a free trial or a free monthly allowance.
  • You are in control. A notice to tell people they are being transcribed, an anonymous mode, automatic deletion and a one-click erase.

Read what happens to your data, service by service.

Press Record and see who said what.

Works in Chrome or Edge on a computer. Nothing to install, no account.

Open ZumiScribe

Want captions on phones, the sound of a single app, or fully private transcription on a Mac? Get the ZumiScribe Local app.