Skip to content
AquillaAquilla Help

Your preferences

Everything under Preferences is about you, not any one project. Open it from the account menu in the sidebar (your username, then Preferences), or go to aquilla.app/preferences. The page’s own words set the scope: “Personal preferences that apply to you across all projects.” Most of these settings live in your browser, though, so they follow you per device, not per account. The Recording settings are the exception: while you’re signed in, they follow your account.

Preferences save as you change them, with Saved beside the setting. A text field, such as Name when signed out or a translator profile answer, saves when you leave it, not on every keystroke. See There is no Save button.

The top of the Preferences page: the General card with Theme, App font size, UI language, Name when signed out and Share usage data, then a Workspace row reading Top bar and a Recording row reading Follows you, each with an arrow, and the start of AI & personalization with Translator profile reading Not set
The General card comes first. Workspace and Recording each open a page of their own; AI & personalization and Account follow below.

General

Section titled “General”
  • Theme: follow your system appearance, or pin Light or Dark on this device.
  • App font size: “The overall size of menus, sidebars, settings, and editor cell text,” from Small through Default to Large and Extra large. A file’s own editor settings can still set a bigger or smaller size on top of this for one side of one file; reset there to follow this size again.
  • UI language: “The language the app’s own interface (menus, buttons, messages) is shown in.” This is separate from any project’s languages and from the AI’s reply language. The choices include Swahili (Kiswahili) and Hindi (हिन्दी); see Switching the app’s own language for every language offered.
  • Name when signed out: “Used as the author of your edits when you work without signing in.” This used to be the Username in each project’s settings; that old spot now says “This setting moved to Preferences → General.” with a Go to it link that opens this row.
  • Share usage data: product analytics, on or off. The description is explicit about the boundary: “Usage events, like creating a project or exporting, and session recordings that help us diagnose problems. Never the contents of your translations or files.”
  • Workspace: where the editor sidebar’s tab strip lives (Left rail or Top bar), and whether replacing an existing translation asks for confirmation first.
  • Recording: how the recorder and the timeline work for you. See Recording below.

Recording

Section titled “Recording”

Recording opens from the General card. Its hint reads Follows you when you’re signed in and This device only when you’re not. While you’re signed in, “They follow you: change one here, in the recorder or on the timeline, and it changes on every device where you’re signed in.” Each row has an (i): click it and what the row does opens under it.

The Recording preferences page. Its intro reads How the recorder and the timeline work for you, and says they follow you on every device where you're signed in. The Recorder group lists Countdown with Off, Fast, Normal and Slow (Normal chosen), Countdown beep with its (i) open underneath, Move on after saving a recording, Keep the takes drawer open, Recording format with WAV and Compressed (WAV chosen), Show the film beside the recorder, and Play the film's sound while recording, switched off. The Timeline group lists Follow playhead and Snap to neighboring edges. Every row has an (i)
Preferences → Recording, with the (i) beside Countdown beep open.

Under Recorder:

  • Countdown: the recorder counts 3, 2, 1 before each take. Fast, Normal and Slow give each number half a second, one second or a second and a half; Off starts recording as soon as you press Record.
  • Countdown beep: “A short beep on each number of the countdown, so you can keep your eyes on the line.” With the countdown off there’s nothing to beep, so the switch is greyed out and keeps its setting until the countdown is back.
  • Move on after saving a recording: saving takes you to the next line, and on the last line closes the recorder. An uploaded file stays on its line.
  • Keep the takes drawer open: lists the line’s takes under the recorder.
  • Recording format: WAV keeps full quality and a take can run to 15 minutes; Compressed files are much smaller and can run to 30 minutes. A take keeps the format it was recorded in.
  • Show the film beside the recorder: turn it off to open the narrow recorder; its Video button brings the film back.
  • Play the film’s sound while recording: off unless you turn it on. Use it only with headphones, or the film’s sound goes into your take.

Under Timeline:

  • Follow playhead: while playing, the timeline scrolls to keep the playhead in view, and lets go if you scroll away by hand.
  • Snap to neighboring edges: a take or line you drag snaps to the edges next to it.

AI & personalization

Section titled “AI & personalization”

Translator profile is the interesting one: a short, entirely optional form the AI reads so “its summaries and answers fit your context — and so it replies in your language.” The assistant answers me in (your reply language, which wins over the project’s), age, education, translation experience, geographical setting, and anything else you want it to weigh. All of it stays on your device.

The Translator profile form with optional fields for assistant language, age, gender, education, religious background, translation experience, and geographical setting, filled in with Spanish, first project, and an urban Latin America setting
A few optional facts about you, and the AI's answers and summaries start fitting your situation.

AI provider keys holds your personal key override: a key saved here is used for your own AI calls across projects on this browser, on top of whatever each project configures. The section says which key is in use: “In use in every project that doesn’t have its own provider.” once you’ve set one, or “Not set. Projects use Aquilla unless they have their own provider.” when you haven’t. On-device AI models starts with a Transcription choice (Aquilla hosted (recommended), with a Hosted model list under it, or Local Whisper in this browser, see Audio & voices) and manages the on-device models (Whisper transcription and the local voices), which download once and are shared by every project on the device. If your browser has no usable graphics card (hardware acceleration switched off, or a remote desktop, for example), local Whisper switches to a slower mode that runs on the processor instead of showing Failed. Expect longer waits, not an error.

Account

Section titled “Account”

Notifications sets how much comment email Aquilla sends you: Every mention and reply, Only when someone @-mentions me, or Never. Replies on one thread always arrive as a single email conversation, however you set it.

Usage shows your recent AI and audio activity: requests today, audio generated today, and a 7-day audio history. While you’re in an organization, it also shows how much of that organization’s AI for this week has been used, as a percentage, under the organization’s name.

API tokens mints personal access tokens for the Agent API, so an external agent or script can act with your access. Each token gets a name, a scope (an organization, optionally narrowed to one project), an expiry, and a mode:

  • Ask — every write waits for your approval.
  • Act — writes apply immediately. Requires a project below where you’re a maintainer.

The token’s plaintext is shown once at minting; after that it can only be revoked. Treat it like a password, because the page says exactly that. Approving agent changes walks through what a connected agent’s requests look like and how the Ask mode’s approvals work.