Moqi Product Introduction (English)

One line

In meetings, AI that helps you answer — not just understand.

The problem

Caption tools solve "understanding what was said." Moqi solves the next step: when it's your turn to speak, answering well. Especially for people working in a non-native language — you understand, you can speak, but organizing a complex answer in seconds under pressure is hard.

Core features

• Two-track live subtitles: you (microphone) and the other side (system audio) on separate tracks — the capture itself knows who spoke, no guessing.
• Answer prompt cards: seconds after a question lands, answer points appear on your screen only — keywords bilingual (including your native language), full sentences in the meeting language, ready to speak.
• Pre-meeting material (optional): cards work without it. Load the product brief, the pricing, the JD or the CV and they get more precise — and quote your own words. If a number is not in the material, the card says so instead of inventing one.
• Five scenario models: job interview (I'm the candidate) / job interview (I'm the interviewer) / sales call / customer support / general meeting — card organization follows the scenario. The interviewer scenario is not a renamed role: the cards run the other way, suggesting what to probe next rather than answering for the candidate; the general scenario groups cards by what the other side just said (question, request, pushback, pending decision, plain update).
• Turn prompt cards off mid-meeting (since build 112, all four platforms): in a meeting where you do not need to speak, switch them off from the prompt-card panel header; while they are off no prompt-card request goes to the model — subtitles, translation and the summary carry on — and you can turn them back on any time.
• Tell Moqi what you mainly use it for (since build 124, all four platforms): first-time setup asks one question, "What will you mainly use Moqi for?" — sales calls, customer support, meetings at work, a job interview as the candidate or as the interviewer, or something else. Your pick sets the matching default call type ("Something else" changes nothing), and the answer is not sent to Moqi's servers. Settings > Meetings has a "Main use" row where you can change it later; people who finished setup earlier are not asked again.
• Android shows the microphone in use (since build 124): the face-to-face and online-meeting screens show which microphone Moqi is listening to — the phone's own, or your headset's name — as iPhone does.
• Cards are less likely to invent a security, privacy or compliance commitment (since build 125, all four platforms): when someone asks about a certification, an encryption method or where your data is stored and the material you gave Moqi does not cover it, the card now suggests confirming and following up instead of making an answer up. Questions the material does answer are handled as before. This is much less likely, not impossible — a card can still occasionally overstep, so check anything you are about to promise.
• Your own subtitles are tucked away by default (since build 106): the other side's words get the full width; your side is still recorded, and the archive, the full text and copy-all include both sides. On Mac and Windows a Layout menu places the panels side by side or stacked, puts the prompt cards first or second, and resets the arrangement.
• One-click summary & archive: every meeting is saved as a record the moment it ends — you never have to remember to archive it — and archives live only on your own device. Any time afterwards you can summarize it as one of five formats: Short summary (the default) / Detailed summary / Follow-up email / Checklist / Mind map (since build 111). The mind map groups the meeting by topic with decisions and actions marked; on Mac and Windows it is a collapsible tree you can save as a PNG, on phones a collapsible outline. On Mac and Windows the summary window opens larger and can be resized, so long summaries and mind maps are easier to read (since build 118). When the summary is in a language other than your app language, one tap translates it to English or Chinese (since build 92) — the translation is shown on your device only and never written into the archive.
• Meeting history and archives (all four platforms): browse past meetings; opening one shows the summary first, with the transcript folded behind it. "Meeting records" are the ones not summarized yet, "Archived" are the ones with a summary — two states of the same data. Summarizing a meeting again never replaces the previous summary: every one is kept and the newest is shown by default; a meeting with more than one can be expanded in the list, one row per summary (format · language · time), and each can be read, copied or deleted individually (since build 116). A saved meeting can be renamed (since build 113) or deleted (it asks first; on a Mac it goes to the Trash, and on Windows to the Recycle Bin since build 122). After a meeting you can edit its transcript (since build 119): fix words the speech recognition got wrong and delete lines you don't need. The first edit keeps a copy of the original, which you can restore with one click or delete. Summaries you already made stay as they are; a new summary uses the edited transcript. On Mac and Windows the history window can be resized and the reading text size adjusted, and your size is remembered (since build 115). Point the archive folder at your own cloud drive and both machines read the same files (one format, both platforms).
• Translation under the other side's subtitles when their language differs from yours (since build 76): on by default, collapsible any time — collapsing hides the line on screen, the translation stays in the copied text and in the archive.
• Maximize either pane (since build 76): a button in the top corner of the prompt-card and subtitle panes; press once to fill the window, press again to restore the split you dragged.

Works with headphones on (the structural difference vs a hardware recorder)

Moqi captures at the system-audio layer — it takes the meeting app's own output stream, not the air in the room. Wear noise-cancelling headphones, AirPods, anything: the other party's voice is still captured.

By contrast, any air-listening hardware recorder captures only your half of the conversation in that setup — and a summary built from half a conversation isn't merely incomplete, it reads complete while reaching the wrong conclusions.

Basis: multiple rounds of owner testing with headphones during early development (including real interview sessions). ⚠️ Invalidation: both platforms' capture paths have changed since. To attach a build number to this claim, re-confirm once on the current build.

Where your data goes (stated plainly)

Audio goes straight to the transcription provider and does not pass through our servers; transcripts are forwarded through our servers to the model vendor, and we do not store them; meeting archives and logs stay on your own device. Capture never starts before an explicit consent confirmation, revocable at any time — after withdrawal, even results already in flight are discarded. Until there is an account system, no personal information is collected: your invite code is your entire identity.

Platforms

Infrastructure (one line)

Two-region backend with automatic client-side failover: if the primary dies mid-meeting, subtitles and prompt cards recover within about half a minute — measured on macOS, Windows and iPhone, not aspirational.

Beta caveats

• Transcription accuracy depends on accent / noise / domain vocabulary; cards can occasionally miss. Screenshots of cards saying something untrue are especially welcome — "a card promising something the product doesn't do" is a top-priority defect here.
• The Windows installer is not code-signed yet; SmartScreen will warn.
• First launch needs an invite code (up to 4 live codes per person, sharing one quota). Get one on the request page: https://app.moqiai.app/invite (if the page is down, email support@moqiai.app instead).

Join the beta

1. Open https://app.moqiai.app/invite, leave your name and email and pick a platform (Windows / macOS / iOS / Android). A person reviews each request; once approved, the invite code and install steps arrive by email (up to 4 live codes per person sharing one quota; if you lose it, request again with the same email — you get an extra code, your installed devices keep working, up to 4 live codes).
2. Once approved, follow the install steps in that email and paste the invite code at first launch.
3. Feedback by replying to the email; screenshots of cards saying something untrue are the most useful thing you can send. If the request page will not load, email support@moqiai.app and say which platform you use.

Screenshot guide