// AI TOOLS · QWEN SCRIBE

Qwen Scribe

A free, open-source macOS app that runs Alibaba's Qwen3-ASR speech model entirely on Apple Silicon — private file transcription plus system-wide dictation, with no cloud, account, or API key.

KompozyTurn one idea into a week of content — across every platform, published for you.
Get Started →

Last verified · 2026-07-29 · by Moe Ameen

What Qwen Scribe is

Qwen Scribe is a free, open-source macOS app that does two things privately and entirely on your own machine: it transcribes audio and video files, and it acts as a system-wide dictation tool. It's an independent community project by a developer who goes by VladUZH, published on GitHub under the Apache-2.0 license, and it surfaced publicly as a Show HN in 2026. Its own one-line pitch is "private, local transcription and system-wide dictation for Apple Silicon."

The engine underneath is Alibaba's Qwen3-ASR speech-recognition model, run through the mlx-qwen3-asr port so it executes on the Mac's Metal GPU rather than a cloud API. You choose between two model sizes: a 1.7B model tuned for accuracy that needs roughly 3.4 GB of unified memory, or a 0.6B model tuned for speed that needs around 1.2 GB. The first transcription downloads the chosen weights once; after that the app works offline. Nothing — audio or transcript — leaves the Mac, and there's no account, API key, or subscription anywhere in the flow. The project is explicit that it is not affiliated with, endorsed by, or sponsored by Alibaba Cloud, the Qwen team, or Apple.

The two workflows are distinct. For files, you drag audio or video into a local web interface and get back an editable transcript with word-level timestamps, automatic language detection (with an option to force a language and add vocabulary hints), and an SRT subtitle export. For dictation, you hold the right Command key while focused in any text field, speak, and release — Qwen Scribe transcribes on device and inserts the text at your cursor, with a small heads-up display for listening/transcribing states that's designed not to steal focus. A local, searchable transcript history lets you reopen, delete individually, or clear everything.

Two honest caveats. It's Apple Silicon only and needs macOS 14 or newer, Python 3.12+, and FFmpeg for non-WAV media — so Windows, Linux, and Intel-Mac users are out. And it's early: at the time of writing it's version 0.1.0-beta.1, distributed as a source build (you compile it locally with `make app`; signed, notarized binaries are slated for a later release), and saved transcripts are stored as readable, unencrypted JSON.

What you can make with it

  • Private, offline transcripts of interviews, podcasts, and meetings that never leave your Mac
  • System-wide voice dictation into any text field — hold right Command, speak, release
  • SRT subtitle files exported straight from a transcribed audio or video file
  • Word-level timestamps for locating exact moments in a long recording
  • Auto language-detected transcripts, with optional forced language and custom vocabulary hints
  • A searchable local history of everything you've transcribed or dictated

How Kompozy turns Qwen Scribe output into content

The most underrated thing Qwen Scribe unlocks isn't transcription — it's dictation as a capture method. Because you can hold right Command and talk into any text field, you can narrate a content idea the second it lands: the hook for a video, the angle for a carousel, the rough outline of a newsletter, all spoken aloud and typed on device without a keyboard or a cloud round-trip. The problem is that a spoken draft is still just raw words in a text box. Kompozy is what turns that captured voice into finished, on-brand, published content — so the pairing is "talk it, then ship it."

Concretely: dictate your idea or a loose script anywhere on your Mac with Qwen Scribe, then paste that text into Kompozy as a source. From that one spoken draft Kompozy generates across formats — a Persona or HeyGen avatar video that delivers your script on camera, Clipped Shorts, brand-exact Carousels via HyperFrames, Photo Posts, Quote Graphics, a Blog Article, an Email Newsletter, and Text Posts — every piece governed by your Persona Brief so a rushed, spoken-out-loud thought comes out sounding like your brand. Kompozy then reframes each piece per destination and schedules and publishes across eight social platforms plus blog and email through Autopilot and a per-post review queue. Qwen Scribe removes the keyboard from ideation; Kompozy removes everything between the idea and a week of published posts.

  1. Install Qwen Scribe on your Apple Silicon Mac and grant it microphone, input-monitoring, and accessibility permissions for dictation.
  2. Hold the right Command key in any text field and talk through your content idea, hook, or rough script; release to drop the transcript in.
  3. Paste that dictated text into Kompozy as a source.
  4. Generate the set from it — avatar video, Clipped Shorts, Carousel, Quote Graphics, Blog, Newsletter, Text Posts — all held to your Persona Brief.
  5. Reframe per platform and schedule the batch across eight social platforms plus blog and email with Autopilot and per-post review.

Frequently asked questions

What is Qwen Scribe?

Qwen Scribe is a free, open-source (Apache-2.0) macOS app for Apple Silicon that transcribes audio and video files and provides system-wide voice dictation. It runs Alibaba's Qwen3-ASR model locally on the Mac's Metal GPU via mlx-qwen3-asr, so audio and transcripts stay on your machine — no cloud, account, or API key. It's an independent project by VladUZH, not an official Alibaba or Apple product.

Does Qwen Scribe work offline?

Yes, after a one-time setup. The first transcription downloads your chosen model weights (a 1.7B accuracy model needing ~3.4 GB of memory, or a 0.6B speed model needing ~1.2 GB); once the dependencies and weights are cached, it runs fully offline with nothing sent to any server.

What are the requirements to run Qwen Scribe?

An Apple Silicon Mac running macOS 14 or newer, Python 3.12 or newer, and FFmpeg for non-WAV audio or video. Dictation also needs microphone, input-monitoring, and accessibility permissions. There's no Windows, Linux, or Intel-Mac support, and at v0.1.0-beta.1 you build it from source with make app rather than installing a signed binary.

How do you dictate with Qwen Scribe?

Focus any text field, hold the right Command key, speak, then release. Qwen Scribe transcribes on device and inserts the text at your cursor, showing a small non-intrusive heads-up display for listening and transcribing. A local searchable history keeps your past transcripts, which you can reopen or delete.

Can Qwen Scribe create or publish content?

No. It produces a transcript or dictated text and stops there — it doesn't design posts, generate video, caption for a feed, or publish. To turn a dictated draft into finished content, pair it with a content engine like Kompozy, which generates video, carousels, images, a blog, and a newsletter in your brand voice and publishes them across platforms.

Related tools

  • YapA free, open-source macOS voice dictation app that transcribes on-device with Apple's Speech framework — press a shortcut, talk, and your words land in whatever field you were typing in, with no cloud, no account, and no model to download.
  • Apple SpeechAnalyzerApple's on-device speech-to-text framework — a new proprietary transcription model, introduced at WWDC 2025, that benchmarks against OpenAI's Whisper.
  • Transcribe.cppOpen-source C/C++ library that runs 16+ speech-to-text model families locally on your own GPU via the ggml runtime — accurate, offline transcription with no per-minute API bill.
  • Video Transcriber AIA browser-based AI transcription platform that turns video and audio into editable, searchable text — upload a file, paste a YouTube or Zoom link, get a speaker-labeled transcript with timestamps, and optionally translate it into another language, all with no install and a free no-sign-up tier.

← All AI tools · Get started →