What we leave out
No built-in document editor, no “second workspace,” no social layer. You stay in Slack, the IDE, the browser—Voxera is a thin pipe, not a new place to live.
What sets Voxera apart
Most voice tools only dump new text at the cursor. Voxera is one of the few voice-input apps that treats highlighted text as a first-class target: select a phrase in Slack, a doc, or an IDE—speak how it should change (tighten, rephrase, fix tone)—and get a precise replacement right there, with optional AI proofreading on Pro. Caret dictation and your vocabulary are part of the same minimal hotkey workflow. We keep the stack deliberately small: one hotkey, a slim bar, no second workspace. Why we leave features out.
Installer downloads are not available yet.
Product principle
Plenty of tools keep stacking modes, dashboards, and side apps. Voxera goes the other way: we optimize a single loop—and we double down on a workflow most dictation apps skip: selection + spoken instruction → replaced text—alongside plain caret dictation. Everything else has to earn its place.
No built-in document editor, no “second workspace,” no social layer. You stay in Slack, the IDE, the browser—Voxera is a thin pipe, not a new place to live.
Dictionary, optional proofreading, screen context, and voice shortcuts exist because they directly improve dictation, replacement, or injection—including when you’re commanding selected text, not only inserting at the caret.
A compact bar and straightforward settings mean fewer panels and toggles. The goal is to press the hotkey and forget the app until the text appears.
Voice-first workflow
Nothing selected? Hold the hotkey, speak, release—new text lands at the caret. Text highlighted? The same gesture turns your voice into an instruction about that selection—rewrite, shorten, formalize—then replaces it in place. On Pro, an LLM can polish before inject or replace. Few voice apps wire both paths this cleanly; we built Voxera around that pair.
Get the appWhy teams pick Voxera
The same minimal loop everywhere: capture voice, optionally refine language, inject or replace selection—without leaving the window you’re in. That “speak to the highlight” capability is rare in a crowded dictation market; we’d rather do one job well than bundle half-related tools you’ll never open.
Type less in Slack, email, Notion, terminals, and IDEs. Voxera injects at the caret—and when you’ve highlighted something, your voice drives the edit (replace or refine) in that same focused field.
A compact floating bar stays out of the way. Dictate in bursts or longer passages; processing is tuned for responsiveness on real hardware.
Optional on-screen context nudges the model toward the vocabulary already in front of you—helpful for code, product names, and UI copy.
Developers & power users
Route spoken phrases to keyboard shortcuts and actions. Pair that with a dictionary tuned to your stack so logs, APIs, and framework names survive transcription intact—and use the same stack with selection + voice instruction when you want to reshape a block of code or prose without retyping it.
Map keywords to shortcuts—run macros, submit forms, or trigger editor commands without memorizing new chords.
Outcomes
Less repetitive typing, faster updates, and fewer context switches between voice memos and the apps where work actually happens.
Communication
Speak a rough update at the caret; get a concise paragraph—or select a messy line and dictate the instruction (“make this professional,” “shorten for Slack”). Voxera replaces the selection in place. That’s the workflow we put up front: fewer paste hops, clearer async updates for support and leadership.
Long-form
Capture briefs, specs, and narrative text without fighting the keyboard. History stays on your machine so you can revisit past sessions when you need to reuse wording.
Platform
Capabilities we ship are tied to the core workflow—caret dictation plus voice-driven edits on selected text—nothing ornamental. Advanced controls for accuracy, privacy-minded defaults, and a path to Pro when you outgrow the free tier.
Speech-to-text tuned for real-world microphones and accents, delivered through Voxera’s managed API path.
Highlight content in any focused app, speak how it should change, and replace it in place—a workflow few dictation products prioritize. Caret-only insertion is the common default; Voxera treats your selection as a first-class target alongside fresh dictation.
Teach Voxera names, brands, and technical tokens so they appear correctly in output.
Set tone, formatting, and rules—formal email one moment, casual chat the next—especially powerful when you’re steering a selected passage.
Native-feeling hotkeys and platform-appropriate text access so injection and selection replacement feel natural on each OS.
Review past transcripts from your device; keep a paper trail without leaving the app ecosystem you trust.
Optional cloud sync for settings and dictionary when you log in—pick the balance that fits your team.
Early adopters
Indie hackers, operators, and engineers use Voxera to stay in flow. Want your logo here? Reach out as we grow the public reference list.
Pricing
Free tier stays honest and lean: core transcription within monthly limits. Pro adds only what heavy users need—proofreading, custom instructions, richer voice-on-selection editing, a larger dictionary, and screen context—without turning Voxera into an all-in-one platform.
Sign in with Google first, then continue to our payment provider to finish checkout—your Voxera account is linked the same way as in the desktop app.
Prices shown in the graphic above; subject to change—see checkout for current billing.
Grab the latest build for your platform. Files are served from public GitHub Releases.
Installer downloads are not available yet—we’ll publish Windows and macOS builds here when ready.