Your workspace

Welcome back

Capture a conversation, upload a recording, or continue where you left off.

Saved items 0 No activity yet
Live AI credits Loading Minutes available
Recording storage Loading
Checking storage
Library

Recent sessions

Workspace

Record, transcribe, and work with your transcript

Speak, share a tab, or capture system audio — words appear as you go. Summarize, translate, ask questions or study it with the transcript still in view.

Ready Timer00:00 EngineBrowser SourceMicrophone
Ready
Off
Original
Press the mic and start talking. A speaker name appears under each time marker — click it to switch who was talking, double-click to rename or add someone new.
0 words · 00:00
Include when copying or exporting
Export
Summary
Translate
Ask
Insights
Study
Summary

Turn transcripts into notes

Summarizes whatever is currently in your transcript, including speaker labels. Powered by Oralyvo™'s secure backend — your API key is never exposed to the browser.

Your summary will appear here once you generate it.
Export
Translate

Read your transcript in another language

Translates whatever is currently in your transcript. Speaker labels and timestamps are kept as-is.

Your translation will appear here once you generate it.
Export
Ask

Ask questions about what was said

Answers come only from what was actually said — if it isn't in the transcript, you'll be told so rather than given a guess.

Record something in the transcript, then ask away.
Insights

See the shape of the conversation

Stats are counted from your transcript in this browser. Highlights are found by AI.

Timeline

Timestamps appear here once you record.
Study

Turn a transcript into revision material

Questions and flashcards are drawn only from what was said.

Read along

Follow text as it's spoken

Load a document and either read it aloud yourself or let Oralyvo™ read to you — each word highlights in sync.

Load a .txt, .docx, or .pdf to read along with
Follow my voice
Text-to-speech
Tap the mic, then start reading the text out loud
Speed 1.0x
Upload

Transcribe a recording

Drop in an audio file and get a full transcript — timestamps included, ready to save, export or run through Summary and Translate.

Drag an audio file here, or

Up to 60MB. Files over 24MB are split into parts and transcribed in sequence automatically — this takes longer. MP4 video works too — the audio is extracted automatically.

How Oralyvo™ works

What each part does, what to change, and what your current device supports.

History

Everything you've saved

Saved transcripts and summaries. Stored on this device, and also to your account if you're signed in (Profile).

Profile

Your profile

Sign-in and personal details — synced to your account wherever you use Oralyvo™.

Sign in to also save your history to your account, so it follows you across devices. Fully optional — everything keeps working locally without an account.

Settings

Configure Oralyvo™

Appearance, AI provider, transcription engine, vocabulary and data — all stored locally except where noted.

Appearance

Dark mode
Switch between light and dark themes

AI provider

Pick which engine generates your summaries and translations. Unavailable ones aren't configured on this deployment yet and can't be selected.

Data

Back up history to a file
Encrypted is readable only by Oralyvo™. Plain text is a readable JSON file you can open anywhere, but anyone with the file can read it.
Restore history from a file
Merges with what's already saved here — nothing is overwritten
Record audio while transcribing
Saves the audio so you can replay it and tap any [time] marker to jump there. Off by default — if transcription ever misbehaves on your phone, turn this off first. Audio is stored on this device only.
Audio input source
Choose what Oralyvo™ should hear. System Audio and Mic + System use your browser's screen/tab sharing picker; make sure Share audio is enabled. On unsupported browsers or mobile devices, use Microphone.
Microphone
Pick which microphone Oralyvo™ uses, and test it before a long session.
Transcription engine
Live AI is the recommended engine — automatic speaker detection and the most accurate real-time recognition, via Oralyvo™'s secure backend. Falls back to Whisper automatically if it's ever unavailable. Whisper Live sends continuous 16 kHz audio to your own persistent WebSocket server.
My templates
Your own one-click formats. One per line as Button name = instruction, for example Youth session = Write case notes with concerns raised, support offered, and follow-up needed. They appear on the Summary tab.
Custom vocabulary
Names, jargon, and acronyms the recogniser keeps getting wrong. One per line as heard = correct, for example tall you = Tolu. Applied automatically as you transcribe.
Saved history
Stored in this browser only, never uploaded

About

Oralyvo™
Published by WianTribe Inc.
v3.0
Admin

Manage accounts

Visible only to admin and super_admin accounts — server-enforced, this tab is just a convenience.

Users
Content
Features
Announcements
Audit Log

Content — Guide tab

Edits are saved as a draft until you publish — the live Guide tab keeps showing the published version until then.

Feature flags

Announcements

Only announcements with status "active" (and within their date window, if set) show in the banner at the top of the app.

On accuracy: By default, Oralyvo™ uses your browser's free built-in speech engine, so accuracy depends on your mic, background noise, and accent match — picking the closest language/accent above helps. Speaker labels are manual (tap to switch) on this engine. Signed-in users can switch to Live AI in Settings for automatic speaker detection and more accurate recognition via a paid cloud engine. Summaries are generated server-side through Oralyvo™'s own secure backend, so no API key ever touches this browser.

Oralyvo™ — © WianTribe Inc.