# KeepMyTalk

> KeepMyTalk is a free browser-based AI meeting transcriber for English speech. Capture a meeting tab, your microphone, or both. Save, search, edit, and export transcripts.

## Product facts

- Price: free to use. No subscription or credit card required.
- Privacy: Audio is processed on the device and never uploaded. You explicitly enable temporary local buffering before recording; processed audio is deleted and pending sections can be recovered in the same browser. Transcript text and meeting metadata are saved to the account on the server.
- Requirements: Google account, internet connection, and a capable desktop device. Chrome or Edge is recommended for tab audio. First use downloads roughly 70–105 MB of model, runtime and speech-filter files.
- Limitations: English only. Audio is processed in short windows, so captions are delayed and accuracy varies. Screen and system audio support depends on the browser and operating system. Hosting and database quotas apply. Offline application startup is not supported.
- Exports: TXT, Markdown, JSON.

## Public resources

- [Website](https://keepmytalk.online/): product overview, free offering, and FAQ.
- [Help](https://keepmytalk.online/help): capture setup and sign-in troubleshooting.
- [Privacy](https://keepmytalk.online/privacy): audio processing, transcript storage, and deletion.
- [Terms](https://keepmytalk.online/terms): consent, costs, and availability.
- [Product JSON](https://keepmytalk.online/.well-known/product.json): public capabilities and authenticated workflow boundaries; a custom description, not an execution protocol.

## Account access

[Create an account](https://keepmytalk.online/signup) or [sign in](https://keepmytalk.online/login) with Google. Account operations require the user's authenticated session. Capturing audio requires explicit browser permission and participant consent. Unattended capture is not supported. No private transcripts are included here.

## Frequently asked questions

### Is KeepMyTalk really free?

Yes. KeepMyTalk is free to use, with no subscription or credit card required. Meeting transcription, your transcript library, search, editing, and exports are included. Your device runs the speech model. Hosting and database quotas still apply; free usage does not mean unlimited capacity or guaranteed availability.

### Do I need to install anything?

No browser extension is needed. After sign-in, about 68 MB of default Fast speech files download in the background to this browser. Local AI initializes on New transcription. The optional Detailed model downloads when selected (roughly 105 MB including runtime and filter). A recent desktop browser and a capable laptop are recommended.

### Can I transcribe Google Meet, Zoom, or Teams?

Share the browser tab containing your meeting and enable audio in the browser picker. Browser-based meetings work when an audio track is provided. Capturing a native desktop meeting depends on your browser and operating system.

### Does it work on Mac and Windows?

Tab audio is the recommended path in desktop Chromium browsers. Whole-screen and window audio vary by operating system. Microphone capture is a separate option. See Help for testing status.

### Can I capture my microphone?

Yes. Choose microphone only, tab audio, or both. Use headphones when combining sources to reduce echo and duplicate speech.

### Can I use KeepMyTalk on my phone?

You can sign in, read, search, edit and export transcripts on a phone. If your browser supports secure microphone capture and AudioWorklet, microphone mode is available; meeting-tab and other app audio are not a reliable mobile workflow. Keep the recording page open and the screen awake. Local AI speed and memory requirements vary, and physical iOS/Android recording remains unverified. Try a short transcription first, or use desktop Chrome or Edge for meeting tabs.

### Does it work offline?

The model may be cached after downloading, but signing in, loading the application, and saving to your account require a connection. Offline application startup is not supported.

### Where are my transcripts stored?

Text, timestamps, and meeting metadata are stored in the deployment’s PostgreSQL database and scoped to your account. Audio is processed in your browser. Opt-in pending audio is temporarily buffered on your device and deleted after recognition; it is never uploaded.

### Can I export or delete my data?

Export each transcript as TXT, Markdown, or JSON. Delete individual transcripts in the library, or delete all transcripts and your account in Settings.

### Why is my transcription delayed?

Draft recognition starts with about 1.5 seconds of captured audio, plus device processing time. Draft words may change as more context arrives; only finalized text is saved. Busy devices update drafts less often to prioritize final text. If recognition falls behind, listening continues while pending audio is buffered on your device. Storage exhaustion or browser/device interruptions can still stop capture with an explanation. Accuracy is imperfect; review important details.

### What happens if I close my browser?

Completed text is saved incrementally. A temporary, account-specific recovery copy is kept in this browser until saving succeeds. Committed pending audio and checkpointed text can be recovered from New transcription in the same browser and account. The last partial window may be lost. Sign-out, private-mode closure or clearing site data removes local recovery.