Speak naturally. Get polished text.

AI voice input that turns your spoken words into clean, professional writing — in any language or mix of languages.

Request beta access View pricing

From voice to structure

Say it out loud — Vox organizes your words into structured, professional output.

What you say
okay so after the meeting... we need to get the design done by Friday, and um the backend team should start on the API, oh and also someone needs to book the conference room for next week's demo, I think that's about it
What Vox organizes
Here are the follow-ups from today's meeting: 1. Complete design by Friday 2. Backend team: begin API development 3. Book conference room for next week's demo

Built for professionals

Designed for people who think in multiple languages and need polished output fast.

Software Engineer

Write documentation and messages faster

Dictate PRs, code reviews, and Slack messages. Vox handles the formatting so you can stay in flow.

Academic Researcher

Draft papers and notes effortlessly

Speak your ideas in any language mix. Vox converts them into clean academic prose ready for editing.

Global Team Member

Bridge the language gap

Working across multiple languages? Vox understands mixed-language speech and produces coherent text in your natural voice.

Core capabilities

Multilingual recognition

Seamless recognition of mixed-language speech. No language switching needed.

Spoken to written

AI-powered rewriting transforms conversational speech into clean, professional text.

Global infrastructure

Service nodes in Hong Kong and Singapore. Built on global cloud infrastructure for reliability and low latency.

Personal dictionary

Vox learns your terminology. Custom dictionaries and automatic term learning ensure accuracy for your domain.

Simple, transparent pricing

Start free. Upgrade when you need more.

Free
$0
300 minutes / month
Start free
Standard
$4.99 /mo
2,000 minutes / month
Get started
Pro
$14.99 /mo
5,000 minutes / month
Get started

See full comparison →

Frequently asked questions

What is Vox?
Vox is an AI-powered voice input tool for macOS. It captures your speech, recognizes multilingual and mixed-language content, and rewrites your spoken words into polished, professional text — then pastes it directly where your cursor is.
What languages are supported?
Vox handles multilingual and mixed-language speech seamlessly — speak naturally in any language or combination. The interface supports 8 languages: English, Simplified Chinese, Traditional Chinese, Japanese, Korean, Spanish, French, and Brazilian Portuguese.
How is my voice data handled?
Your audio is processed in real-time and not stored after transcription. We do not retain voice recordings. Transcription results are stored locally on your device in an encrypted database. See our Privacy Statement for full details.
What happens when I reach my free limit?
You will see a notification with the option to upgrade. Your existing transcription history and dictionary remain intact. The free quota resets at the beginning of each calendar month.
Can I cancel anytime?
Yes. You can cancel your subscription at any time from your account settings. Your plan remains active until the end of the current billing period, and you will not be charged again.