See your mic go live. Speak, polish, and paste. Dictate locally on your Mac and talk to AI agents. No account. No subscription.
Download Free100 free dictations · 50 notes · 10 meeting recordings · No credit card
brew install muvon/tap/vextmacOS 14+ · Apple Silicon · No account required
One shortcut. One pill from microphone to paste.
Hold your hotkey. Speak when the pill turns red: your mic is live.
Speak naturally. Watch your words appear in the pill with local Parakeet.
Release. Follow Transcribing, then Polishing. Esc skips AI. Failed take? Keep the audio and Retry.
Follow one pill from mic startup to pasted text. Meet the Press-to-Paste HUD in Vext 1.5.1.
Retry If a take fails, its audio is kept. Retry directly in the pill.
Dictate, record meetings, and capture notes. Keep it all local by default.
Hold a hotkey, speak, release — text appears at your cursor. Works in any app, any text field.
Record with speaker labels, get full transcripts, screenshots, and AI-generated summaries.
Quick voice remarks — transcribed, cleaned up, and stored locally in the app for later.
Choose how your words read. Keep them As spoken, Clean up the wording, or choose a style for each app.
"so um I was thinking we should uh probably move the deadline to like next Friday because ah the team needs more time to finish the uh the integration tests"
"We should move the deadline to next Friday — the team needs more time to finish the integration tests."
Choose As spoken, Clean up, Email, Message, Bullet points, Formal, or Custom. Set styles per app. Esc skips AI polishing.
Paste the raw transcript without AI reshaping.
Tidy grammar, punctuation, and filler words.
Shape your dictation for correspondence or a concise chat reply.
Organize a list, use a formal tone, or write your own instruction.
Local by default. Speech and AI models run on Apple Silicon. Nothing is uploaded unless you add your own API key.
Dictate with Parakeet TDT v3 through FluidAudio, or choose Apple Speech. Polish with a local MLX model.
Download the models once, then dictate and polish offline. License validation connects to Vext’s server.
Start without an account. Vext has no telemetry SDKs or usage tracking.
100 free dictations, 50 notes, and 10 meeting recordings to start. Then one price, unlimited use.
$0 in year 2
$120–360/year
Unlock from within the app when you're ready. Free updates included. Major new versions at 50% off for existing owners.
Feature-by-feature against the leading voice and meeting tools.
| Vext $49 once | Wispr Flow $12–15/mo | Granola $14–35/mo | Otter.ai $8–17/mo | |
|---|---|---|---|---|
| Dictation (paste at cursor) | ||||
| Meeting transcription | ||||
| Voice notes | ||||
| Speaker labels | ||||
| Cross-meeting voice recognition | N/A | |||
| AI text cleanup | ||||
| Meeting summaries | ||||
| Translation | ||||
| Screenshot capture (any mode) | ||||
| Screenshots auto-paste to AI | N/A | N/A | ||
| YOLO mode (auto-submit) | N/A | N/A | ||
| Live transcript while you speak | ||||
| Per-app dictation styles | ||||
| Fully local, no cloud required | ||||
| Works offline | ||||
| No bot joins your call | N/A | |||
| Shows when the mic is live · Esc skips AI mid-take | N/A | N/A | N/A | |
| Cost after 2 years | $49 | $288–360 | $336–840 | $200–408 |
N/A: not applicable or not verified.
Updated 5 September 2026 for Vext 1.5.1 and the no-bot row. Other competitor features and prices reflect April 2026; they may change.
Watch live text appear with local Parakeet. Follow transcription and polishing in the same pill, with an elapsed clock.
60 seconds of audio transcribed in ~400ms. On-device.
Let's review the Q3 roadmap and figure out priorities.
I think we should focus on the API redesign first. It's blocking three other teams.
Agreed. Can we have a draft by end of next week?
Record any meeting — Zoom, Google Meet, FaceTime, or in-person — and get a full transcript with speaker identification. Turn on Summarize to extract key points and action items. Both versions are always saved.
Vext detects every distinct voice in your meeting automatically. Name them once — and from your next call onward, the same person is identified, labeled, and color-coded without lifting a finger.
Capture any region of your screen during hands-free dictation. The screenshot pastes alongside your transcribed prompt — straight into Claude Code, Cursor, or any AI tool. Fully hands-free coding.
Check the API rate limits before we push the new integration. Sarah mentioned the sandbox has different thresholds than production.
The onboarding flow needs a skip option on the second screen. Users are dropping off because they think the setup is mandatory.
Try SwiftUI NavigationSplitView for the sidebar instead of the custom implementation. It handles state restoration automatically.
Press a key, say what's on your mind, and move on. Vext transcribes, cleans up, and stores your note locally — ready when you need it.
Speak, then translate before pasting. Choose from 29 target languages. Apply a dictation style in the same AI pass.
"Let's schedule a meeting for next Tuesday to discuss the project roadmap and assign tasks to the team."
"Давайте назначим встречу на следующий вторник, чтобы обсудить план проекта и распределить задачи в команде."
Vext is a system-level service. It works in any text field, in any app — browsers, editors, terminals, email, chat.
Connect Claude Code, Codex CLI, OpenCode, Cursor/Windsurf, Claude Desktop, or Octomind through MCP. Dictate, transcribe files, and read meetings. Manage notes, speakers, and vocabulary.
Listens on 127.0.0.1 only. Every request needs the token Vext generates for you. Off by default.
claude mcp add --transport http vext http://127.0.0.1:58398/mcp --header "Authorization: Bearer TOKEN"Replace TOKEN with the token from Settings — or use the copy button there, which fills it in.
Press a key once to start dictation. Press again to stop. No holding required — just talk as long as you need. Perfect for longer passages or when your hands are busy. Bind it to a mouse thumb button, or let a quick tap of your push-to-talk key toggle it.
Capture screenshots mid-dictation — they auto-paste with your transcript. See how →
Turn it on and Vext automatically presses Return after pasting your transcription. Speak, release, and your prompt is already running.
Stop editing. Stop polishing. Just talk. LLMs know what you mean, even when your words aren't perfect.
When you start recording, Vext automatically fades your system audio so your voice comes through clearly. Release the hotkey and volume returns to normal. No manual adjustment needed.
Run speech and AI locally. Add your own API key if you want cloud models. Off by default.
| Model | Type | Speed | Size |
|---|---|---|---|
| Parakeet Default Parakeet TDT v3 via FluidAudio. Local speech recognition on Apple Silicon. | Local | 150x RT | ~600 MB |
| Apple Dictation Built-in macOS speech recognition. Zero download. | Local | Realtime | Built-in |
| OpenAI-compatible Choose an OpenAI-compatible speech API with your own key. | API | Varies | — |
| Model | Type | Size |
|---|---|---|
| Gemma 3 4B Default Default. Fast, accurate, great balance of speed and quality. | Local | ~2.5 GB |
| Gemma 3 1B Ultra-lightweight. Fastest local option, lower accuracy. | Local | ~1 GB |
| Qwen 3 4B Strong multilingual support. Good for translation tasks. | Local | ~2.5 GB |
| LLaMA 3.2 3B Meta LLaMA. Strong general-purpose performance. | Local | ~2.4 GB |
| Phi-3.5 Mini Microsoft Phi-3.5. Compact, strong reasoning. | Local | ~2.8 GB |
| OpenAI-compatible Choose an OpenAI-compatible AI model with your own key. | API | — |
Vext is built by Muvon Un Limited, a small product studio. We build tools we use every day — designed to work locally, respect your privacy, and get out of your way.