RefineIQ
Add to Chrome
Help

When something sticks.

Nearly every issue is one of the three below. If yours isn't, the guide covers normal setup end to end, and obliviox@zohomail.in reaches the people who build RefineIQ.

01

Microphone permission denied

Voice Draft needs a one-time microphone grant for the extension itself, not for each website. If recording won't start or the pill says microphone access is off:

  1. 1.Click the Voice pill's "Allow microphone" action. It opens RefineIQ's own setup tab, the one place Chrome can reliably show the permission prompt. Click Allow there.
  2. 2.If you previously clicked Block, Chrome won't re-ask. Open chrome://settings/content/microphone, find the RefineIQ entry under "Not allowed to use your microphone", and switch it to Allow, then retry from the setup tab.
  3. 3.On a Mac, Chrome itself also needs the system permission: System Settings → Privacy & Security → Microphone → enable your browser, then restart it.
  4. 4.Check the right input device is selected at the top of chrome://settings/content/microphone. A disconnected headset that's still selected records silence.

Audio never leaves your machine: recording and transcription happen on-device, the permission is revocable any time in the same Chrome settings, and nothing can ever start listening on its own.

02

Voice model download stuck or failing

Voice Draft runs on-device, so it downloads a speech model once (~73 to 195 MB depending on tier) and caches it locally. Text refining needs no download. If the voice model stalls or errors:

  1. 1.Check your connection, and if you're behind a VPN, proxy, or strict firewall, try without it.
  2. 2.Make sure there's enough free disk space: roughly 500 MB free is a safe margin for the voice tiers. Chrome silently evicts caches on a nearly-full disk.
  3. 3.Use the Retry action where the error appeared (popup or the in-page panel). Downloads resume cleanly and progress counts up honestly from where things stand.
  4. 4.Still heavy for your machine or connection? Pick the lighter voice tier in Settings (~28 MB). Smaller, faster to fetch, and transcription still stays on your device.
  5. 5.If a download seems permanently wedged, remove and reinstall the extension. That clears the voice-model cache entirely; settings take a minute to redo.

Once the voice model is cached, dictation works without re-downloading. Audio is transcribed on-device and never uploaded. Only the transcribed text is sent to the backend to be refined.

03

Slow refines

Text refining runs on the RefineIQ backend, so refine speed tracks your network, not your GPU. If refines feel slow:

  1. 1.Use Chrome 113 or newer (or a current Edge, Brave, Opera, Vivaldi, or Arc). RefineIQ requires 113 or newer.
  2. 2.Check your connection. A flaky or high-latency link is the usual cause of a refine that takes several seconds. A VPN or corporate proxy can add latency too.
  3. 3.Confirm you're signed in and have credits. A stalled refine sometimes means the request is waiting on auth; sign in again from the popup.
  4. 4.Pick the "Clean up" mode for a lighter, faster pass when you only need grammar and filter fixes, and "Sound Human" when you want the full rewrite.
  5. 5.Voice Draft is the one part that runs on-device. If transcription is slow, check chrome://gpu says WebGPU is Hardware accelerated, or switch to the lighter voice tier in Settings.

Your text is never stored, never logged, and never used to train any model. It exists only for the millisecond it takes the backend to rewrite it.

Still stuck? Chat with us. We'll ask for your browser and version, which mode you used, and what you expected versus what happened. RefineIQ keeps no logs of your text, so that context is genuinely all we have to go on. Never include your drafts.

or email obliviox@zohomail.in