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. ANY APP. JUST THE WORDS. ────────────────────────────────────────── TrainScription captures 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. Full Desktop mode captures system audio from any app making sound on your machine — not just browser tabs. If your machine can hear it, TrainScription can transcribe it. 0 cloud calls during transcription. 0 external servers processing your audio. 0 bots joining your call. ────────────────────────────────────────── HOW IT WORKS ────────────────────────────────────────── 1. Open your meeting as normal — in a browser tab OR a desktop app. 2. Click Begin Capture. Choose Browser Tab mode to capture a meeting running in Chrome, OR Full Desktop mode to capture any app making sound on your machine. The extension captures two audio streams on independent pipelines — your microphone and the meeting audio — each transcribed on its own channel, so overlapping speech on both sides is captured, not just whichever channel is loudest. A silence gate drops empty chunks per channel before Whisper ever sees them. No server, no API key, no internet connection required during transcription. 3. Watch the transcript appear in real time. Every few seconds a new chunk is transcribed and appended — speaker-labeled with your configured channel names and a precise timestamp. Close the popup at any time — transcription continues. 4. Highlight misfires to train the Brain. See a word the AI got wrong? Highlight it. 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, grouped together. Export any segment or the full session as a .txt or .srt file. Review any past segment to catch and correct misfires after the fact. 6. You bring your AI. TrainScription gives you the clean local transcript — what you do with it is up to you. When you're done, open Recovery and send the transcript to whichever AI platform you already use and trust — with one click. Your instructions and transcript are copied to your clipboard; your trusted AI platform opens ready to receive them. Nothing is sent automatically, and TrainScription never sees the content after it leaves your device. ────────────────────────────────────────── FULL DESKTOP MODE ────────────────────────────────────────── Full Desktop mode captures all system audio — your microphone plus everything your machine is playing. Select your screen from the OS picker, enable "Also share system audio," and TrainScription captures the full dual-channel audio stream the same way it always has. Any desktop application producing audio is transcribed — video conferencing clients, media players, voice chat, recorded webinars — anything making sound on your machine. No browser tab required. The Brain works the same way in both modes — your trained vocabulary corrects misfires automatically, in Full Desktop or Browser Tab sessions alike. ────────────────────────────────────────── AUDIO & VIDEO FILE IMPORT ────────────────────────────────────────── Already have a recording? Import an existing audio or video file — a meeting export, a webinar recording, anything you already have — and run it through the same on-device Whisper pipeline used for live sessions. No live capture required. Your file is read locally in your browser and processed entirely on your device, exactly like a live session. It is never uploaded anywhere, at any point. The Phonetic Brain applies automatically to imported files the same way it does to live sessions — your trained vocabulary corrects misfires before you ever see the transcript. Audio & Video File Import is a Pro feature. ────────────────────────────────────────── BULK EXPORT, BACKUP & RESTORE ────────────────────────────────────────── Export every stored session at once as a single .zip file — no more downloading segments one at a time. Available on Free and Pro. Pro adds Backup Everything: a complete, machine-readable backup of every session and your full Phonetic Brain, packaged as one .zip file. Restore from Backup brings it all back — into a fresh install or a new machine — without losing anything you've already saved. Useful for moving to a new computer, reinstalling the extension, or simply keeping your own copy of everything you've captured. ────────────────────────────────────────── 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. 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. · MANUAL ADD — Already know how Whisper mangles a term? Use the Manual Add form — correct spelling plus the variants Whisper produces. · IMPORT — Restore from a .train.json backup. Share a specialized vocabulary set across installs, or bring your Brain to a new machine. Plain JSON — human-readable and editable. · MANAGE — Made a wrong assignment? Expand any Brain term and remove individual variants — or delete the whole term — with a single tap. ────────────────────────────────────────── EVERYTHING INCLUDED ────────────────────────────────────────── · No Meeting Bot — Works from browser-tab audio or system audio directly. No third-party participant joins your call. · Full Desktop Mode — Transcribe any app making sound on your machine. Not limited to browser tabs. Free tier sessions are subject to the 15-minute cap and other free-tier limits. · Audio & Video File Import (Pro) — Already have a recording? Import it and run it through the same on-device pipeline, entirely offline. · Bulk Export — Export every session at once as a single .zip file. Available on Free and Pro. · Backup & Restore (Pro) — Back up every session and your full Brain vocabulary as one file. Restore it on a fresh install or a new computer. · Dual-Channel, Speaker-Labeled — Your microphone and meeting audio captured on two independent audio pipelines, not merged into one — overlapping speech on both channels is preserved, not dropped. Each line labeled with your configured channel names and a precise timestamp. · Phonetic Brain — Permanently fixes the words AI always gets wrong. Corrections apply automatically in both modes, visible live as highlights in the transcript. · Brain Correction Write-Back — Highlight a wrong word in any transcript, correct it in place, and that fix writes back to the stored segment immediately. Made a wrong call? One-shot Undo is right in the same toast. · AI Summary Handoff — TrainScription gives you the clean local transcript. You bring the AI you already trust. Configure your preferred platform once in Settings — everything is off by default, nothing is ever sent automatically. Choose from three preset styles (Executive Summary, Action Items, Full Notes), modify any preset as a starting point, or write your own one-off custom prompt. One click from Recovery copies your instructions and transcript to your clipboard and opens the platform ready to receive them. You control every send. · Channel Presets — Six built-in label presets: Default, Corporate, Legal, Interview, Medical, RPG. · Silence Auto-Stop — Automatically stops transcription after a configurable period of silence. Warning fires 1 minute before the threshold with a Keep Transcribing option. · Pause Controls — Pause your mic channel, the meeting audio, or everything — without ending the session. · Export to .txt and .srt — Pro users get one-click assembled export of the full session. · Session Recovery — Sessions are automatically segmented and stored. Rename sessions with custom labels. · Auto-Purge by Age — Optionally clear out old Recovery sessions automatically — 30, 60, or 90 days, or Never. Lock any session to exempt it permanently, regardless of age. Off by default. Free and Pro alike. · Session Tags — Tag any Recovery session with your own labels and filter the session list with one click. All sessions tagged "Client Calls" or "Weekly Sync" surface instantly. Bulk export respects the active tag filter — export just the filtered set as a .zip rather than everything at once. Ungated. Free and Pro alike. · Brain Management — Expand any Brain term and remove individual variants or the whole term with a single click. · 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 — Sensitive conversations where routing audio through third-party cloud services is not an option. · Researchers & Interviewers — Capture 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. · Specialized Vocabulary Workflows — Industries with difficult names, product codes, medication names, case names, or campaign terminology. · Anyone Blocked by Meeting Bots — TrainScription never joins. It simply captures from your machine's audio output. ────────────────────────────────────────── 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 (Browser Tab + Full Desktop) · Silence Auto-Stop (5 and 10 minute options) · Pause controls · Export to .txt and .srt after each session · Session naming in Recovery · AI Summary Handoff (single-session) · Bulk Export — all sessions at once as a single .zip file PRO — $9.99, one payment, no subscription, works across devices. · Unlimited session length · Unlimited Recovery sessions · Unlimited Brain slots · Full Desktop mode — unlimited session length, no cap · One-click assembled full session export · Import full Brain vocabulary files (.train.json) · Silence Auto-Stop with all options including Indefinite · Pro Brain Term Picker with type-to-filter and auto-suggest · AI Summary Handoff (full multi-segment session assembly) · Audio & Video File Import — bring your own recordings into the same local pipeline · Backup Everything & Restore — move your full session history and Brain to any machine · Cross-device access via email login · Everything in Free, forever ────────────────────────────────────────── WHY TRAINSCRIPTION ────────────────────────────────────────── · No bot, ever — capture happens directly from browser-tab or system audio, nothing joins your call · Local-first by architecture — audio never leaves your device, no cloud server is ever involved, works fully offline once the model is cached · Built around your vocabulary — the Phonetic Brain fixes your specific jargon permanently, and corrections write straight back to your stored transcripts · Your data is portable — back up and restore your full session history and Brain on any machine · One payment, no subscription — $9.99 once, unlimited sessions forever ────────────────────────────────────────── PRIVACY & DATA ────────────────────────────────────────── · Audio is processed locally using WebAssembly-based Whisper inference in your browser. Audio chunks exist temporarily in RAM and are discarded immediately after processing — never written to disk. · Audio is not transmitted to external servers. TrainScription does not operate cloud infrastructure. · Transcripts and Brain vocabulary are stored locally in your browser's extension storage. Never synchronized or accessible outside your device unless you export them yourself. · No account required for the free version. No analytics, no tracking, no behavioral data collection. · AI Summary Handoff is an explicit, user-initiated feature — not part of the core transcription pipeline. When you choose to request a summary, your transcript is sent directly from your browser to the AI platform you have configured and trust. TrainScription does not see or relay this content. Nothing is sent automatically. The feature is off by default and requires deliberate setup. · Imported audio and video files are read locally in your browser and processed entirely on your device, exactly like a live session — never uploaded anywhere, at any point. · Bulk export, backup, and restore are entirely local operations. Building an export file, packaging a backup, and restoring from one all happen in your browser, on your device. No network request is made in either direction. External connections, fully disclosed: a one-time AI model download from the model provider, cached locally; ExtPay license verification for Pro users (payment only); and — only when you explicitly request it — your transcript sent directly to your chosen AI platform via AI Summary Handoff. Your audio is never involved in any external connection. ────────────────────────────────────────── PERMISSIONS — WHY THEY'RE NEEDED ────────────────────────────────────────── · Microphone — Captures your local microphone channel during transcription sessions. Only active when you initiate a session. · Tab Audio — Captures meeting audio from the active browser tab. Only active when you initiate a session. · Desktop Audio (Full Desktop mode) — Captures system audio from your selected screen source. Requires you to actively pick a source from an OS picker. Only active during a Full Desktop session. · Storage — Saves transcripts, Brain corrections, and settings locally on your device. Nothing stored outside local extension storage. · Downloads — Used only when you explicitly export a transcript or Brain backup. · Tabs — Opens your chosen AI platform in a new tab only when you explicitly request a summary via AI Summary Handoff. 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.