Hold a shortcut and speak. Let go, and it transcribes, removes filler words, smooths the sentences, and drops the polished result right at your cursor. Your recordings, data and API credentials all stay in your own hands.
So So I looked at the the flow, and I think like the overall icons and layout, and the text too, I think we should optimize it — consider centering you know, consider… arranging it nicer, otherwise the the background feels empty, and then the text is just too cramped, and it sits a bit too high. The layout just doesn't feel great I guess.
Recording, recognition, clean-up, paste-back — we tell you exactly where each step goes. We're honest about the one step that uses the cloud, and never dress up cloud calls as “fully offline”.
Recordings, history and API credentials are stored on your own device by default, never passing through any server of ours.
Use your own Volcengine / Qwen / Zhipu accounts. Switch recognition and clean-up models freely, never locked to one provider — and we never bill you.
Mac, iPhone and the keyboard share one core codebase, with unit tests and CI build checks — dependable enough to live in your daily workflow.
These four are real output from the real product pipeline — casual spoken takes on the left, Typefree's automatic clean-up on the right: fillers removed, slips fixed, sentences smoothed, points split out, numbers and terms normalized.
I can come Friday afternoon, no wait, not Friday, it's Thursday afternoon, anytime after 3 — can you set it up?
Thursday afternoon, anytime after 3 works for me — can you set it up?
I'm a bit happy today, but also a bit annoyed. Happy because someone finally said that feature is useful; annoyed because I found a whole pile of details still to fill in. Like on one hand it feels promising, on the other there's more to do. Maybe this is just what it feels like once a product actually starts getting used.
I'm a bit happy today, but also a bit annoyed. Happy because someone finally said that feature is useful; annoyed because I found a whole pile of details still to fill in. On one hand it feels promising, on the other there's suddenly more to do. Maybe this is just what it feels like once a product really starts getting used.
Can you fix this login page — uh no, don't overhaul it, first look at why the button keeps spinning. Then if the frontend state isn't resetting, fix the frontend; if the API isn't responding, add the error message. Also don't touch the signup page, and run the tests at the end.
Can you fix this login page. Don't overhaul it — first look at why the button keeps spinning. 1. If the frontend state isn't resetting, fix the frontend; 2. If the API isn't responding, add the error message. Also, don't touch the signup page, and run the tests at the end.
I worked out the quote — the basic plan is around 3,600 a year, the pro plan about 9,800 a year, and buying three years should be about 20% cheaper.
I worked out the quote: 1. Basic plan: about ¥3,600 a year; 2. Pro plan: about ¥9,800 a year. Buying three years should be about 20% cheaper.
The whole thing usually takes a second or two, and every step is visible and traceable.
Hold your chosen shortcut to capture audio; release to stop and processing begins immediately.
Calls the ASR provider you configured to turn speech into text, injecting your hot words.
Longer passages go to the LLM you configured to remove fillers, smooth sentences and tidy formatting.
A final pass applies your glossary, then the polished text is pasted straight at your cursor.
Mac, iPhone and the keyboard share the same core code — same recognition, same clean-up, same hot words, identical behavior everywhere.
Lives in your menu bar. Hold the shortcut in any text field and speak; a floating window shows volume and progress, and text lands automatically when you let go.
Voice clean-up on your phone. Press and hold to speak, view input stats and history, and share the same config and glossary as your Mac.
A system-wide custom keyboard. Tap the mic in any app to speak, and the polished text lands right in the current field.
We lead with privacy, but we never dress up cloud calls as “fully offline.” We're honest about the step that uses the cloud, and keep everything else in your own hands.
Audio is captured on your device and only enters processing after you let go.
Requests go directly to the ASR and LLM you configured — never through a server of ours.
API keys, history and original audio are kept on your own device first.
After a glossary pass, the result is pasted straight back at your cursor.
To be precise: your requests go straight to the cloud providers you configured, not through Typefree — and we're honest about the step that uses the cloud, never passing it off as “fully offline.”
Beginners can run on defaults; power users can swap models, tune the glossary and review history to fit it precisely into their workflow.
Recognition uses Volcengine BigASR; for clean-up, switch anytime between Qwen, Zhipu GLM and Doubao, choosing by cost and quality.
Add easily-misheard product names, people and English tool names to your glossary, with optional weights. Both recognition and clean-up will prefer them.
Every entry is stored locally with the raw transcript, the cleaned result, timing and usage. Swap a model or add new hot words and re-process the same take.
Optionally keep each original recording (macOS) to replay and verify. Set retention yourself — 1 day, 1 week, 1 month or forever.
Download and use it free, 1,000 characters a day. Need unlimited? Buy once, use forever — not a subscription.
Great for everyday and light use.
Unlock unlimited input. Pay once, use forever — not a subscription.
Checkout is coming soon (cards, WeChat Pay & Alipay via Paddle). For now, contact us by email to purchase.
Beginners just install and grant permissions; power users can go further with providers, hot words and glossary.
Download the signed, notarized DMG and drag it into Applications. The free version gives 1,000 characters a day — try it first, buy the lifetime version once you're happy.
Enter your recognition and clean-up API keys — you obtain them yourself from Volcengine and Qwen; Typefree never relays or bills. First time? Follow the step-by-step guide and you're done in 5 minutes.
Grant microphone and accessibility permissions, hold the shortcut in any field, speak and let go — the text lands at your cursor.
System dictation is closer to word-for-word transcription — it types out every “um” and “you know.” Typefree cleans the language after recognition — removing fillers, smoothing sentences, normalizing numbers and punctuation — so the output is ready to send or use as a prompt.
No. The main path calls the cloud recognition and LLM services you configured. The emphasis is local-first and never routing through a server of ours — not “works without internet.”
Recognition uses Volcengine BigASR; clean-up supports Qwen, Zhipu GLM and Doubao, switchable anytime — or you can choose “no polish, output raw text.”
Yes. The free version gives 1,000 characters a day, plenty to evaluate it; for unlimited input, buy the lifetime version once for $19 — forever, not a subscription. Full refund within 14 days if you're not satisfied.
Right now it suits users willing to set up provider credentials. The guide has sign-up links and instructions (a 5-minute walkthrough); if you just want to see results, check the demo on this page.
Recordings, history and API credentials are stored on your own device by default (on macOS, ~/.config/voicepolish/). Requests only go to the providers you configured, never through us. You set how long history is kept.
For people who care about where their data goes, want to buy once, and don't want to be locked into a subscription. Start free, upgrade when you need more.