Recording
Start, pause, and stop a recording and watch the live transcript
Recording
A recording is the heart of a Foxl note. While you record, Foxl streams your microphone audio to a live transcript and writes it into the note as it goes.
Start a recording
Press Start Recording in the top bar (on the desktop the tray menu's New Recording does the same and jumps to Notes). Foxl asks for microphone permission the first time, then begins capturing immediately. A red dot and a running timer show that recording is active.
By default Foxl transcribes with Amazon Transcribe on your own AWS account: the desktop app signs the connection from the AWS credentials already on your computer (a profile, an SSO session, environment variables), so there is nothing to paste and no Foxl sign-in. If something is missing, the Notes screen says so before you press record - a Finish setting up Notes notice names what is absent (AWS credentials, or a model provider for the summary) and links to the pane that fixes it. See Where the audio goes below for the other engines.
On the desktop, Foxl also records the other participants' voices playing on your Mac (meeting apps, browser tabs) alongside your microphone, so a call on headphones is not one-sided. This is Capture system audio under Settings > Notes > Recording, on by default; macOS asks once for System Audio Recording permission, and the pane has a Test system audio button to check it.
The live transcript
As you speak, the Transcript tab of the right-hand panel fills in line by line:
- Speaker labels. Foxl groups speech into "Speaker 1", "Speaker 2", and so on, each in its own colour. Click a label to rename the speaker - the new name applies across the whole transcript and keeps a colour of its own. With two or more speakers a talk-time bar at the top of the transcript shows how long each has held the floor. (AssemblyAI and OpenAI do not separate speakers while streaming; every other engine does.)
- Live notes. Each finalized line is also appended into the note editor on the left, so by the end of the meeting you already have a written record.
- Partial vs final. Words may appear faintly first (a best guess) and then firm up - that's the transcriber settling on the final text.
The transcript and the AI assistant share one panel on the right, as tabs. Drag the panel's left edge to make it wider or narrower - Foxl remembers the width - or hide it with the panel button in the top bar when you want more room for the editor.
The Live panel
On the desktop app a floating, always-on-top glass panel opens when a recording starts (it is controlled by Meeting HUD under Settings > Notes > Recording, and the Live panel button in the top bar opens it any time). It carries Live, Suggest, Notes and Background tabs, its own start / stop / pause controls, an ask bar for the assistant, one-tap chips (Agree, Push back, Ask, Suggest), a Mini mode caption pill for screen sharing, and an Options menu for transparency, text size, theme, always-on-top and live translation. It survives Stop, so it can run across back-to-back meetings. The Suggest tab holds live reply suggestions (see AI summary & assistant).
Pause and resume
Press Pause to stop capturing without ending the recording - useful for a break or an off-the-record moment. Press again to resume. The timer pauses with you.
Stop a recording
Press Stop to finish. Foxl saves the note, names it from what was said (Auto title, on by default) and, if Auto Summary is on and a model provider is connected, immediately writes a structured summary (see AI summary). On the desktop a copy is also written to your auto-save folder (see Exporting & saving). The finished note appears at the top of the sidebar list.
If the transcription engine refuses mid-recording - an expired AWS session, a key that has run out of quota, or Foxl Relay credits running out - Foxl shows the engine's own explanation and stops the recording rather than running on with an empty transcript. The live text already written into the editor stays on screen, but no note is filed and the audio is not kept, so fix the cause and record again.
Languages
Foxl transcribes many languages. Set your spoken language under Settings > Notes > Recording (Korean, English, Japanese, Chinese, Spanish, German, French or Portuguese), or leave it on Auto-detect, which lets the engine identify the language and leans toward the app language. The interface language is separate and lives under Settings > General.
Where the audio goes
By default transcription runs on Amazon Transcribe in your own AWS account. Under Settings > Notes > Recording (the pane is headed Recording and transcription) you can send the audio somewhere else instead, and the choice applies to live recordings, imported audio files and Dictate anywhere:
| Destination | What you need | Who bills you |
|---|---|---|
| Amazon Transcribe (default) | AWS credentials on this computer, and a region | AWS, directly |
| On device (Apple Silicon, offline) | an Apple Silicon Mac and a one-off download of about 1.3 GB (plus about 33 MB for speaker labels), from the Install engine button in this pane | nobody - the audio never leaves your Mac |
| Deepgram | a Deepgram API key | Deepgram, directly |
| AssemblyAI | an AssemblyAI API key | AssemblyAI, directly |
| OpenAI | an OpenAI API key | OpenAI, directly |
| ElevenLabs | an ElevenLabs API key | ElevenLabs, directly |
| Foxl Relay | an account Foxl has enabled for it - the option is hidden otherwise | Foxl credits, by the second of audio |
Paste the API key into the field that appears under the provider you picked. It is stored encrypted on your computer, is used only to open the transcription connection, and is never sent to Foxl.
Two things to know before you switch. A pasted key and the on-device engine both need the Foxl desktop app - it is what opens the connection or runs the model - so the phone and app.foxl.ai cannot use them: pick Amazon Transcribe there (it works through your desktop, see Recording on mobile), and the on-device option is simply not offered on those devices. And AssemblyAI and OpenAI do not separate speakers while transcribing live, so with either of those the whole transcript is attributed to one speaker. Amazon Transcribe, Deepgram, ElevenLabs, the on-device engine and Foxl Relay all label speakers. Foxl tells you which is which under the provider you pick.
On device (offline, on your Mac)
The On device engine runs speech recognition on your Apple Silicon Mac's GPU - nothing is uploaded, nothing is metered, and it keeps working with the network off, which suits a confidential conversation or a machine with no internet. Pick it under Settings > Notes > Recording and press Install engine: a one-off download of about 1.3 GB that lives outside the app, so a Foxl update does not fetch it again. A second small download (about 33 MB) adds speaker labels, and Settings offers Install engine once more if you installed before those existed. Auto-detect lets it guess the language per utterance. It cannot translate the other party live, it prefers treating two very similar voices as one person over splitting one in two, and it is offered only on an Apple Silicon Mac - not on the phone, the web app, or a Windows or Linux desktop, where the option is greyed out with the reason.
Dictate anywhere
The transcription engine you pick here also backs Dictate anywhere - hold a shortcut, speak, and the cleaned-up text is typed wherever your cursor is, in any app. It is a desktop feature with its own pane at Settings > Notes > Dictate anywhere (its own shortcut, spoken language and cleanup model).
Recording from another screen
A recording keeps running even if you switch to Foxl Agent, Foxl Code, or open Settings. A small Recording pill with the running timer appears at the bottom-right while you're away - click it to jump back to the note, or drag it somewhere else; Foxl remembers where you put it.
Import an existing recording
Foxl can transcribe an audio file you already have. On the desktop, drag the file onto
the Notes window or use File > Import Recording... (Cmd+O / Ctrl+O). On the phone, tap
Import a recording on the Notes home screen. Common formats work, including .m4a,
.mp3, .wav, .mp4, .aac, .flac and .ogg.
Transcription runs at roughly the speed of the audio, so a 30-minute recording takes about 30 minutes. Foxl shows a progress bar with the file name and a live percentage while it works, and names the note it created when it finishes. You can leave the screen - or the app - while it runs, and Foxl will notify you when the transcript is ready (see Notifications).
If a file contains no recognisable speech - a silent stretch, music only, or audio in a language other than your transcription setting - Foxl still creates the note with the audio attached, so you can play it back, change the language, and run it again rather than starting over.
Recording on mobile
On the iOS and Android apps, recording uses your device microphone, and the iPhone keeps recording while the screen is locked or you are in another app. Start and stop work the same way as on desktop; the phone home screen adds Add context for better AI, Import a recording and a Recent list, and an open note switches between Summary, Transcript, Notes and Report with a segmented control.
Which engine the phone can use depends on your desktop:
- Amazon Transcribe (default) - your computer must be running Foxl and reachable through the desktop relay when you press record. It hands the phone a one-hour, transcribe-only pass, so the meeting keeps going even if the computer then goes to sleep. If your AWS login cannot issue such a pass (an SSO session, for example), the phone instead asks your computer to sign each five-minute renewal, so it has to stay awake.
- Your own API key and the on-device engine are desktop-only. The on-device option is not offered on the phone; a pasted-key provider falls back to Foxl Relay where your account has it.
- Foxl Relay works with no computer involved, but only on accounts Foxl has enabled for it. On any other account, a phone with no reachable desktop cannot record, and the message says which destinations to pick instead.