Three capture modes
Tab audio only, voice memo (mic only), or dual (tab + mic). Switch with one tap depending on the scene.
Popup → mode segmented control
Help & Resources
Get the most out of
Get the most out of
Voice to Workflow.
Quick start, feature guides, FAQs, and the latest updates — every resource you need to make voice-driven automation truly yours, all in one place.
Quick start
Five steps to turn your voice into automation.
From install to your first webhook, the shortest path. Each step takes seconds.
-
1
Install
Click "Add to Chrome" on the Chrome Web Store. Chrome 116+ required. The extension icon appears in your toolbar instantly.
-
2
Register a webhook
Open Options and add your webhook URL — Zapier, Make, Slack, n8n, anywhere. Register one webhook per workflow, as many as you need.
-
3
Pick a capture mode
Open the popup and choose from three modes: tab audio, voice memo, or dual (tab + mic). Switch between them at any time.
-
4
Start capturing
Hit "Start capture" to begin. Use ⏸ to pause during breaks and ▶ to resume — the timer stays accurate throughout.
-
5
Pick the destination
Auto-send to your default webhook — or use "Ask each time" mode to pick from registered webhooks or save locally at capture end.
Feature guides
Shape voice into the workflow you want.
How you capture, where you send, how you integrate AI, where you save. Every core capability, distilled for quick reference.
Pause & Resume
Built for breaks, interruptions, and long sessions. State is preserved even if you close and reopen the popup.
Recording bar → ⏸ / ▶ buttonsPick destination at capture end
Use "Ask each time" mode to pick a registered webhook or save locally — the moment capture ends.
Popup → destination segment → Ask each timeOne webhook per workflow
Multiple Zapiers, Makes, Slacks, n8ns — across one stack. Any workflow in your stack, one voice away.
Options → Workflow WebhooksBYOK (Bring Your Own Key)
Use your own OpenAI / Anthropic / any AI key for transcription and summaries. Scope and cost stay under your control.
Configure the API key inside your workflowLocal save
Save to any folder via Chrome Downloads. Useful as a fallback when webhook upload fails, or for offline captures.
Options → Local save → Save folder
Frequently asked questions
Start here, when in doubt.
Setup, capturing, sending, data handling. The questions that come up in real-world use, gathered here.
My microphone isn't recognized / capture won't start
On first launch, the browser prompts for microphone permission. If you didn't grant it, check and grant the extension's mic access in chrome://settings/content/microphone. Tab-audio-only mode does not require microphone permission.
If the mic is still not recognized, check that the input device is not muted in your OS sound settings, and that another app (e.g. Zoom) isn't holding the microphone exclusively.
Capture is too quiet / too loud
In Options → Audio processing, adjust microphone and tab audio gains independently (0.1 – 3.0). If the mic feels quiet with echo cancellation on, try enabling the Volume boost (Compressor).
If tab audio is overwhelming, lower the source (video / webinar) volume and keep the extension's tab gain at 1.0 — that usually produces a natural balance.
What happens when a webhook send fails?
On send failure, a result tab opens automatically. Your capture is held in memory, and you can retry with another registered webhook or fall back to local save.
By design, this does not rely on system notifications — so even with Windows Focus Assist or notifications off, you won't miss it. The tab itself surfaces as the recovery surface.
Where does my captured audio go? Is it stored on Fixus servers?
No. Captured audio is processed locally, or sent only to webhook URLs you have registered. Nothing reaches Fixus servers. AI transcription and summaries run inside your own workflow, using your own API keys (BYOK).
For full details on data handling, see our Privacy Policy.
Can I run multiple workflows on the same webhook service in parallel?
Yes. You can register as many webhooks as you have workflows — multiple Zapiers, Makes, Slacks, or n8ns can coexist, each pointed at its own endpoint.
Typical setup: one webhook for meeting notes, one for task creation, one for archival — pick which to send to at capture end via "Ask each time" mode.
It's β — how will features evolve from here?
Voice to Workflow is free during β, and we keep adding and refining capture, routing, and integration features. Early users experience new capabilities first.
For the latest updates, see the "What's new" section below.
Which browsers are supported?
Chrome 116 and later. Built on Manifest V3, leveraging tabCapture / offscreen / Web Audio APIs. Behavior on Chromium-based browsers like Edge or Brave is not officially verified.
What's new
Always evolving.
Throughout β, we ship feature additions and improvements continuously. Early users experience them first.
Help & Resources, now live
- Help center is here — quick start, feature guides, FAQs, and the latest updates, all in one place.
Now on the Chrome Web Store
- Three capture modes — tab audio, voice memo, and dual (tab + mic). Switch with a single tap.
- Pause & resume. Pick the destination at capture end with "Ask each time" mode.
- Register a webhook per workflow — countless destinations, one voice away. If a send fails, instantly switch to another webhook or save locally.
- Meeting-grade audio processing. Echo and noise are tamed, your voice stays present. Mic and tab gains, independently tunable.
- A no-friction dark UI. Japanese and English, auto-following your browser language.
Coming up: we're planning feature additions that further extend the voice-driven automation experience. Updates land here as they ship.
Other inquiries
Every resource you need, in one place.
The guides, FAQs, and updates above resolve most scenarios. If you still need to reach out, the channels below are available.
Fixus Studio
Fixus Voice to Workflow is built and maintained by Fixus Studio, the development brand of Fixus LLC. Questions, feature requests, and issue reports for the extension are accepted through the channels listed.
Your feedback feeds directly into the continuous updates we ship throughout β.