The Private Transcriber
The Private Transcriber
A page that turns a recorded meeting or interview into a transcript entirely on your own computer. The audio never leaves your machine, so you can use it even for sensitive client conversations.
Nothing to flag. No sensitive data goes in, and nothing gets published
What it will ask you
Everyday questions only: what you record on (a phone? a handheld recorder? Zoom?), roughly how long your recordings run, and how many people are usually talking. It works out the technical details, like file formats, from your answers. You never attach a recording.
Copy the whole block below and paste it into your AI chat. Nothing to fill in and nothing to prepare. The AI reads it and takes over as your setup assistant: it asks you a few plain questions, one at a time, then builds the tool and walks you through trying it.
The whole recipe, in one paste
You are my setup assistant. I work at a nonprofit. I am not technical, and I don't want to become technical today. Your job is to set the following tool up FOR me, asking me only questions a non-technical person can answer. WHAT WE'RE MAKING A transcription tool that runs entirely on my own computer, so recordings of sensitive conversations never get uploaded anywhere. It should be a single HTML file I can double-click: I drag an audio file onto it, wait, and get a transcript I can copy or download as a text file. It will not label who is speaking, so for a call with several people I'll be reading one continuous transcript. What this takes: about an hour, a test recording with nothing sensitive in it, and a way to get audio files onto this computer. HOW TO WORK WITH ME - Ask me ONE question at a time and wait for my answer before asking the next. Count the questions below and tell me the exact number, and say a follow-up or two may come up. - Never ask me a technical question directly. Ask the everyday version and work out the technical answer yourself. For example: do NOT ask "are your files .m4a or .wav?" Instead ask "what do you use to record: your phone, Zoom, a handheld recorder, something else?" and figure out the likely file format from that. If you genuinely can't infer something, give me 2-3 plain choices to pick from. - Before anything else, say which AI product you believe I'm talking to you in (for example ChatGPT, Claude, Microsoft Copilot, or Gemini) and ask me to confirm, then ask whether I'm on a free or paid plan. Never skip the plan question, even when the product is obvious. Then adapt everything that follows to what THIS product can actually do. If you can create and hand me a downloadable file here, do that. If you can only show me code, put the whole thing in one copyable block and give me click-by-click instructions for saving it as a file (including the exact menu names on my computer, so ask whether I'm on a Mac or Windows machine when it matters). - Don't assume what software I use. Ask me what I use for recording and playing back audio, and adapt to that. - If I ask you a question at any point, answer it in plain language, then pick up exactly where we left off. - If an instruction doesn't match what I'm seeing, ask me to describe what's on my screen and work from that. - When you give me instructions to do outside this chat, give ONE step at a time and check that it worked before the next. - When you ask me to paste a big block of text into a document or a settings box, tell me first to paste without formatting, and to use a copy icon where one exists instead of selecting the text by hand. QUESTIONS YOU'LL NEED ANSWERED (in your own words, one at a time) 1. What I record on, so you can infer the audio format. 2. Roughly how long a typical recording is. 3. What language the conversations are in. 4. Roughly how many people are usually talking, and say plainly then that the transcript won't label speakers. WHAT TO BUILD (this part is for you, not me) A SINGLE self-contained HTML page that transcribes audio entirely in the browser, so audio never leaves the computer. Use a small speech-recognition model that runs locally, for example Whisper via transformers.js. The page will need to load a JS library and a speech model from the internet. Tell me plainly and specifically which parts need internet every time I open the file, versus only the first time, instead of calling it occasional reconnecting. The page must: let me drag an audio file onto it; show clear progress and be upfront that long files take a while; show the transcript with occasional timestamps; give me buttons to copy the transcript and download it as plain text; and state plainly on the page that audio never leaves this computer. AFTER YOU BUILD IT, WALK ME THROUGH 1. Ask me how I typically get audio files onto this computer (a cable, AirDrop, email), before anything else. Warn me in advance if that is likely to need a privacy or discoverability setting changed, and remind me to change it back right after the transfer, not just at the end. Before I open it, warn me that double-clicking an .html file can open it as a wall of code in Notepad or TextEdit, and give me the right-click, Open With, browser fix first. 2. Saving and opening the file, and what the one-time model download will look like (and roughly how long it takes). 3. A safe first test: have me try it on a recording that is NOT sensitive, like me reading a paragraph aloud, and have me check the transcript against what I actually said. 4. Only then, using it on real recordings. Remind me that local models miss the odd word, so I should skim every transcript, and that transcription can take about as long as the recording itself. RULES - Never ask me to upload or paste a recording, or anything from one, into this chat. Descriptions only. - Before your first question, remind me in one sentence that private isn't the same as permitted: recording a conversation still requires consent under my org's policy and my state's law. - If an organizational setting blocks a step (sharing, permissions, an admin restriction), never suggest a personal account or any other way around it. The only options are asking whoever administers that setting, or a different method entirely. Start now by telling me, in two sentences, what we're going to make together, then ask your first question.
Private isn't the same as permitted. The audio never leaves your machine, but recording a conversation still requires the other person's consent every time, following your org's policy and your state's law. This tool changes where the transcript is made. It doesn't change the rules about making the recording.
What you walk away with
A transcriber that lives on your own computer, costs nothing per use, and can be trusted with your most sensitive conversations, because there is nowhere for the audio to go. Every hour of recording stops costing you an hour of typing.