FAQ

If your question is not here, the troubleshooting guide covers specific symptoms, and privacy architecture answers data questions in far more depth. Anything still unanswered: contact@openvoiceflow.com.

Frequently asked

Is OpenVoiceFlow really free?

Use is free for everyone, including at work, with no account or trial period. If you enable optional cloud cleanup you pay your chosen AI provider directly for tokens.

Does my voice leave my Mac?

No. Audio is transcribed on-device by Whisper and discarded once text exists. There is no code path that uploads audio. If you turn on cloud AI cleanup, the resulting text is sent to the provider you chose under your own key; choosing Ollama or leaving cleanup off keeps everything local.

Does it work offline?

Yes. After the one-time model download, dictation works in airplane mode — the usage-sharing sync (if you've left it on) is fire-and-forget and never blocks it. With cleanup and usage sharing both off, no network request is made at any point.

Which Macs are supported?

macOS 14 Sonoma or newer, on both Apple Silicon and Intel. One universal build covers both. For macOS 12 to 13 a retained 0.3.6 Apple Silicon build is available, but it is end-of-life.

Is there a Windows, Linux, iPhone, or Android version?

Not today. OpenVoiceFlow is macOS-only. iOS and Android versions are in development but cannot be downloaded yet.

How accurate is it?

That depends on your microphone, accent, vocabulary, and model choice far more than on anything we could benchmark. Whisper's larger models are widely regarded as excellent. The honest test takes a minute: dictate a real paragraph of your own work and judge the result.

Can I say punctuation out loud?

Not in version 0.5.27 — saying 'comma' produces the word 'comma'. Whisper punctuates from sentence structure automatically, and optional AI cleanup fixes grammar and removes filler words if you want more.

Why is my dictionary not working?

The personal dictionary, Know-Me profile, and per-app styles are all applied during AI cleanup. With cleanup set to None, which is the default, they have no effect. Turn cleanup on, or use local Ollama if you want that behaviour without sending text to a cloud.

Which languages does it support?

All 99 languages in Whisper's multilingual set, including Ukrainian, Arabic, Hindi, and Chinese — see the full list on the Languages page. Accuracy outside English depends heavily on model size, so use the largest model your Mac handles comfortably.

What happens if the AI cleanup service fails?

You get your raw transcript. Cleanup is designed to fail open: on a missing key, an error, a timeout, or an unparseable response, the app inserts the on-device transcription rather than losing your words.

Does it collect any analytics?

As of 0.5.7, yes, and it's on by default: an anonymous usage summary (word/time totals, which features you use, your country, and a display name you choose) powers an in-app leaderboard. Never audio, never dictated text, never anything from your dictionary, snippets, or Know-Me profile. Turn it off in Settings ▸ Privacy ▸ "Share anonymous usage & leaderboard rank" — full detail in Privacy architecture's Analytics & leaderboard section. The website separately uses privacy-friendly anonymous page-view analytics — page views plus counts of which links and buttons get clicked — unrelated to the app and tied to no identifier.

How do I get support?

Use the Feedback item in the dashboard sidebar, or email contact@openvoiceflow.com. Include your macOS version, your Mac's chip, your OpenVoiceFlow version, and what you saw versus what you expected — the usage summary is aggregate counts, not diagnostics, so your description is still what gets things fixed.

Can I use OpenVoiceFlow at work with confidential material?

The architecture supports that case: audio never leaves the machine, and with cleanup off or pointed at local Ollama, neither does text. Your organization's own policy still applies, and the public source lets your security team verify the claims. Workplace and other organizational use is permitted at no cost under the AGPL-3.0.

Can I use the code in my own project?

Yes, under the GNU Affero General Public License v3.0. Every integration, derivative, fork, or modified build must keep the required notices and visibly state ‘Based on OpenVoiceFlow by Shimoverse Studios’ with a working link to https://github.com/shimoverse/openvoiceflow, even if it stays private or merely connects through a documented interface. If you distribute a modified version or let others use one over a network, publish its complete corresponding source under the same license and rebrand where required.