An hour of speech, transcribed whole

Ramble is long-form stream-of-consciousness interaction: one recording of up to 60 minutes, transcribed whole. Crash-proof: a reload costs five seconds at most. Capture is raw - echo cancellation, noise suppression and automatic gain are requested off - so the transcription service hears what your microphone heard.

Ramble is exclusively part of Free and Pro. On Open, voice input is the standard browser microphone, which transcribes live as you speak (see Voice: talk to it).

Start a take

Four ways in, all opening the same panel:

Where	What you click
Desktop left nav	the Ramble icon
Mobile drawer	the Ramble menu item
Attachments menu	Ramble · Record audio and transcribe it
Mobile, when minimized	the red bubble, back into the running take

Crash-proof recording

The recording is saved every five seconds, for peace of mind. An application reload, a closed browser or a dead battery costs at most the last five seconds; the next start notifies you of recovered takes - the chip recovered: Recovered from an interrupted recording - the tail may be missing - and you can use them right away. A recovered take always keeps its audio.

Audio cues, in the options, are the same reassurance while you speak: a soft tick every minute says the take is up and listening.

Recording in the background

The panel does not need to stay up. Minimize it and move anywhere in the application - the take keeps recording and saving while you work, on desktop and on mobile alike. Come back, stop the take, and the transcript is ready.

While recording, the close button becomes Minimize. On desktop, the left nav shows the take breathing: a red face that pulses with your voice. On mobile it is a red bubble you can drag anywhere on the screen.

Transcription runs on API keys

Transcription needs an engine of your own: a Deepgram or an OpenAI key, set at Settings › Voice › Input. An OpenAI service you already added counts as one, as does a custom transcription endpoint. Audio goes from your browser straight to that AI service, and the text comes back. Big-AGI's servers are not in that path; there is no server-side transcription. The engine is configured in the options:

One engine transcribes a take - the one you pinned, otherwise the first with valid credentials - and a failure is not retried elsewhere.

Topic detection is on by default and comes from Deepgram. The chips appear on the card, and hovering one highlights its span in the transcript.

The first transcript also triggers a title. It is written once, and a title you typed is never overwritten. Titling sends the transcript's opening and closing lines to a fast model - the one part of Ramble that uses your chat models.

Where the recording lives

Audio bytes stay locally in this browser's IndexedDB, on the machine that recorded them. They never reach a Big-AGI server, and they never sync. Everything else travels: the transcript with its language and topics, the title, dates and review state, and the recording's description - duration, format, capture time, device, and the chat it started from.

A ramble reaches your other devices once two things are true: a first non-empty transcript exists, and you are on Pro pro. A take with no words in it never leaves the device.

The audio stays locally (or is often deleted), so a ramble that arrived by sync can be read but not replayed.

Ramble options

The overflow menu holds five toggles:

Menu item	What it does	Default
Transcribe	Auto-transcribes each take as soon as it stops.
Preserve audio locally	Keeps the audio file after a transcript lands; available while Transcribe is on.	off
Detect topics	Asks for topic labels; Deepgram only.
Audio cues	A soft tick every minute, a tone once saved.	off
Show size gauge	Draws each recording's relative size on its collapsed card.	off

By default, audio is deleted from the device the moment a transcript lands. Silence, failed transcriptions and recovered takes keep their audio. Deleting a ramble deletes its audio immediately.

Once the audio is gone, the transcript can be edited but never re-transcribed. To re-transcribe local audio, clear the transcript in the editor: Transcribe re-arms for another pass.

Import Audio... in the same menu transcribes an existing audio file the same way. Its file name becomes the title, and there is no length or size limit.

Troubleshooting

What you see	What it means	What to do
Recording stopped: reached 60 minute cap	The hard limit. Everything up to it is saved.	Start the next take.
Recording stopped: reached 100 MB cap	The size limit. An hour at this quality is about 55 MB, so the time cap normally trips first.	Start the next take.
Recording interrupted: no audio received	The recorder stopped delivering data for 15 seconds - a suspended tab, or an input device that died. Silence does not trip this.	Check the input device, then record again.
Microphone disconnected	The input device went away mid-take.	Reconnect it; what was recorded is kept.
Audio channel busy	The audio channel was already in use.	Start the take again, or reload the application.
error, with the service's own message	The transcription request was refused.	Fix what the message names, then press Transcribe.
no speech	The transcription ran and found no speech.	Play the take back to check the input, then record again.

A take under 0.6 seconds is discarded.

Related

• Talk to it instead of typing
• What syncs between devices
• What leaves the browser
• Open, Free, or Pro