www.cuevoice.ai
“Cue — Voice-First AI Workspace | Dictation, Meetings & Agents”
Tech check
What the site says about itself, next to what its public page actually loads. Facts only, no verdict: you decide.
AI / agents
“…rief too. Stop Cue Meetings interface preview NOTES An AI-native Markdown editor with voice dictation A rich tex…”E29
What it is
- The Internet Archive has never saved this site, so it is probably new.E31
- The site describes itself as: “Dictate in any app, keep notes as local Markdown, capture meetings, and chat with your saved context in one local-first AI workspace for Mac”E2
- It's built with Next.js and React (common tools for building web apps).E12E13
- In your browser it can ask to use your camera or microphone, keeps a live two-way connection open to a server and runs compiled WebAssembly code in your browser.E15E16E17
- It has sections such as /dictate, /meetings, /notes, /agent, /mcp and /routines.E27E28
- While loading, it called 2 endpoints on its own servers, such as /api/price and /rive/mana-2.0.riv.E19E20
Where your data goes
Analytics & trackingCount visits and record what you do on the page. 2
| www.google-analytics.com | Google Analytics / Tag Manager: Google's visitor analytics and tag loader | 1×E9 |
| www.googletagmanager.com | Google Analytics / Tag Manager: Google's visitor analytics and tag loader | 1×E7 |
CDNs & hostingDeliver files (scripts, images) quickly from servers near you. 1
| unpkg.com | unpkg: open-source file CDN | 1×E8 |
How key features work
Live updates
It keeps live connections open (WebSockets) so content updates without reloading.E16
websocketLoading its content
Its content loads from its own API while you browse (/api/price and /rive/mana-2.0.riv).E19E20
/api/price/rive/mana-2.0.rivCookies and storage
Names only. We never store the values.
Pages and API calls
Pages it links to
//dictate/meetings/notes/agent/mcp/routines/for/blog/updates/roadmap/download/faq/compare/release-notes/llm-info/privacy/terms/_next/imageEvidence
Every sentence above points to one of these. Code references show the file, line:column and the short identifier that matched, never the site's code itself.
Limits
- We only see what your browser sees: code and requests on a first visit, without logging in or accepting cookie banners. What the servers do with data is invisible from outside.
- Site code is usually minified (compressed), so names are partly lost and some code may be only partly analysed.
- Some trackers only load after you accept cookies or log in, so the real list can be longer.
- We visited from a server in the United States. Sites load different trackers and cookie banners in different countries (visitors in the EU usually get a consent banner first).
- The tech check compares the site's own words with what its public page loads. Work done on servers, in private code or in separate apps isn't visible here, so 'nothing found' means not visible on the public page, not that it doesn't exist.
- This text was written from fixed templates because no AI writer was available. It uses exactly the same evidence.
- The code reader hit its size budget on parts of 19 large bundle file(s); those parts weren't fully analysed.
Facts, not judgements: this page describes what the code and traffic show, not anyone's intent. Not financial advice. Case id 8XKu19Bk.