TrainScription

On-device meeting transcription. No bot joins your call. No audio uploaded to the cloud. Speaker-labeled and vocabulary-trained.

Real-time meeting transcription that runs entirely on your device. No bot joins your call. No audio uploaded to the cloud. Speaker-labeled, timestamped, and corrected by a vocabulary brain you train yourself. ────────────────────────────────────────── NO BOT. NO CLOUD. JUST YOU AND THE WORDS. ────────────────────────────────────────── TrainScription captures browser meeting audio locally using OpenAI Whisper running via WebAssembly — directly in your browser, with no network requests during transcription. Your audio never leaves your device. Works with Google Meet, Microsoft Teams (web), Zoom (web), Webex, Discord, and any other browser-based call. 0 cloud calls during transcription. 0 external servers processing your audio. 0 bots joining your call. ────────────────────────────────────────── HOW IT WORKS ────────────────────────────────────────── 1. Open your meeting in a browser tab as normal. 2. Click Begin Capture in the TrainScription popup. The extension captures two audio streams simultaneously: your microphone and the tab audio (the meeting). Both are processed locally by a Web Audio graph. A silence gate drops empty chunks before Whisper ever sees them. The AI runs entirely on your device — no server, no API key, no internet connection required during transcription. 3. Watch the transcript appear in real time. Every 5 seconds, a new chunk is transcribed and appended — speaker-labeled with your configured channel names and a precise timestamp. Open the full Studio view for the live transcript, or leave the popup in the background. Close the popup at any time — transcription continues. 4. Highlight misfires to train the Brain. See a word the AI got wrong? Highlight it in the transcript. A popover appears instantly — assign the correct spelling in one click. That mapping is now permanent. Every future transcript corrects that word automatically, before you ever see it. 5. Sessions are always recoverable. Long sessions are automatically segmented into sealed chunks. All segments from a single session are grouped together. Export any segment or the full session as a clean .txt file. Review any past segment in the live transcript view to catch and correct misfires after the fact. ────────────────────────────────────────── THE PHONETIC BRAIN — THE DIFFERENTIATOR ────────────────────────────────────────── Every AI transcription tool has the same problem: proper names, product names, case names, medication names, campaign terms, company jargon — mangled, every time, in predictable patterns. The Phonetic Brain is the permanent fix. Train it once on a word. It corrects that word on every future transcript automatically, before you ever see the output. It compounds — the more you use it, the more accurate your transcripts become. Every word the Brain corrects is highlighted live in the transcript so you can see it working in real time. Four ways to train: · HIGHLIGHT — Select any misheard word during a live session or while reviewing a past segment. A popover appears — assign the correct spelling in under three seconds. No separate screen. · MANUAL ADD — Already know how Whisper is mangling a term? Use the Manual Add form — correct spelling plus the variants Whisper produces. Instant. · IMPORT — Restore from a .train.json backup. Share a specialized vocabulary set across installs, or bring your Brain to a new machine. The file is plain JSON — human-readable and editable outside the extension. · MANAGE — Made a wrong assignment? Expand any Brain term and remove individual variants — or delete the whole term — with a single tap. No JSON editing required. ────────────────────────────────────────── EVERYTHING INCLUDED ────────────────────────────────────────── · No Meeting Bot — Works from browser-tab audio. No third-party participant joins your call. No external transcription service relays your audio through cloud infrastructure. · Dual-Channel, Speaker-Labeled — Your microphone and meeting audio captured separately. Each line labeled with your configured channel names and a precise timestamp. · Phonetic Brain — Permanently fixes the words AI always gets wrong. Corrections apply to every future session automatically and are visible live as highlights in the transcript. · Channel Presets — Six built-in label presets: Default, Corporate, Legal, Interview, Medical, RPG. Fully customizable per session from the popup. · Pause Controls — Pause your mic channel, the meeting audio, or everything — without ending the session. Critical for when you mute yourself in the call but don't want your in-room conversation transcribed. · Export to .txt — Download any session or individual segment as a clean .txt file. Pro users get one-click assembled export of the full session — all segments merged and formatted. · Session Recovery — Sessions are automatically segmented and stored. Review any past segment in the live transcript view to find and correct misfires anytime. · Brain Management — Expand any Brain term and remove individual variants or the whole term with a single click. No config files, no JSON editing. · Works Fully Offline — After the AI model has been downloaded once and cached, TrainScription requires no internet connection to transcribe. ────────────────────────────────────────── BUILT FOR ────────────────────────────────────────── · Legal, Finance & Consulting — Professionals handling sensitive conversations where routing audio through third-party cloud services is simply not an option. · Researchers & Interviewers — Capture browser-based interviews without routing audio through third-party cloud transcription systems. Locally stored, fully exportable. · Heavy Meeting Users — Stop paying monthly transcription subscriptions. One payment covers unlimited sessions — no per-seat, no per-minute billing ever again. · Specialized Vocabulary Workflows — Industries with difficult names, product codes, medication names, case names, or campaign terminology — where generic AI always gets it wrong. ────────────────────────────────────────── PRICING ────────────────────────────────────────── FREE — $0, no credit card, no account required. · 15-minute session cap · 3 Recovery sessions stored · 3 Phonetic Brain slots · Real-time dual-channel transcript · Pause controls · Export to .txt after each session PRO — $4.99, one payment, no subscription, works across devices. · Unlimited session length · Unlimited Recovery sessions · Unlimited Brain slots · One-click assembled full session export · Import full Brain vocabulary files (.train.json) · Cross-device access via email login · Everything in Free, forever ────────────────────────────────────────── WHY TRAINSCRIPTION ────────────────────────────────────────── · No bot ever joins your call — capture happens from browser-tab audio directly · Audio never leaves your device — no cloud server processes your content, ever · Works fully offline after the AI model is cached — no internet required to transcribe · Fixes jargon permanently — the Phonetic Brain corrects your specific vocabulary on every future session automatically · Live correction highlights — see every Brain-corrected word as it happens in the transcript · One payment, no subscription — $4.99 once, unlimited sessions forever · Works in any browser-based meeting tab — Meet, Teams, Zoom, Webex, Discord, and more ────────────────────────────────────────── PRIVACY & DATA ────────────────────────────────────────── · Audio is processed locally using WebAssembly-based Whisper inference running in your browser. Audio chunks exist temporarily in RAM during transcription and are discarded immediately after processing. They are never written to disk. · Audio is not transmitted to external servers. TrainScription does not operate cloud infrastructure and does not upload your audio for remote processing. · Transcripts are stored locally in your browser's extension storage on your machine. They are never synchronized, indexed, or accessible outside your device unless you export them yourself. · Brain vocabulary corrections are stored locally in browser extension storage. Exports are user-controlled .train.json files that live wherever you save them. · No account is required for the free version. No email, no registration, no profile. · No analytics, no tracking, no behavioral data collection. TrainScription does not use tracking pixels, session recorders, or any analytics tooling. · The extension works fully offline after the AI model has been downloaded. External connections, fully disclosed: The AI model is downloaded once from the model provider and cached locally. Pro license verification is handled by ExtPay — payment processing only. Your audio, transcripts, and Brain data are not involved in either connection. ────────────────────────────────────────── UNDER THE HOOD ────────────────────────────────────────── TrainScription is a Manifest V3 Chrome Extension running OpenAI Whisper via WebAssembly locally in your browser. The AI model is downloaded once from the model provider and cached — transcription itself occurs entirely on-device after that initial download. Audio is processed in 5-second volatile chunks that exist only in RAM. They are never written to disk and are not uploaded for cloud processing. The extension's data policy is architecture, not a promise — the extension contains no code to route your audio externally. The only external connections in this extension: a one-time AI model download from the model provider, and ExtPay license verification for Pro users. Both are unrelated to your content — your audio, transcripts, and Brain vocabulary are never involved in either connection. The Phonetic Brain correction function runs synchronously on every transcript line before it's written to storage. Your vocabulary corrections apply before you see the output. ────────────────────────────────────────── PERMISSIONS — WHY THEY'RE NEEDED ────────────────────────────────────────── · Microphone — Used to capture your local microphone channel during transcription sessions. Only active when you initiate a capture session. · Tab Audio — Used to capture the meeting audio from the active browser tab during transcription. Only active when you initiate a capture session. · Storage — Used to save transcripts, Brain vocabulary corrections, and your settings locally on your device. Nothing is stored outside your browser's local extension storage. · Downloads — Used only when you explicitly export a transcript or Brain backup as a file. Not used at any other time. TrainScription does not use permissions for advertising, tracking, behavioral profiling, or any purpose beyond the transcription workflow described above. ────────────────────────────────────────── LEGAL NOTE ────────────────────────────────────────── TrainScription is intended for lawful, disclosed, and consent-compliant use. Users are responsible for complying with applicable local laws, workplace policies, and meeting platform terms of service regarding transcription and recording.