Cadenza
中文GitHub

Download

Get Cadenza.

For macOS 14 or later, on Apple silicon and Intel Macs.

1.2.0

Released 2026-10-09 · 31.4 MB

Download for macOS
Release notes on GitHubOr download the zipChecksums (SHA-256)

Install in three steps

  1. Open the disk image

    Open the .dmg and drag Cadenza to Applications. Check it with the checksum file if you like (shasum -a 256 -c SHA256SUMS.txt).

  2. Open it

    A copy you built yourself opens normally. A downloaded copy is blocked the first time: open System Settings → Privacy & Security, find the message about the app and choose Open Anyway.

  3. Allow three permissions

    Microphone, Accessibility and Input Monitoring, when asked. macOS asks again after each update because every build is signed ad hoc.

In this release

  • **Early preview.** Cadenza 1.2.0 adds voice translation with its own shortcut, more cloud speech and text recognition services, two more on-device speech models, and quieter speech handling. The package runs on **Apple silicon and Intel Macs, macOS 14 or later**.
  • 中文说明见下方。
  • **Voice translation has its own shortcut and page** (Settings → Translation). Ordinary dictation no longer translates. If you had a language chosen, set a translate shortcut to keep translating.
  • **Shortcuts:** "Hold to talk" and "Tap to start and stop" are two rows, each with its own switch and key. The Hold/Tap choice is gone.
  • **More cloud speech services:** OpenAI, Groq, Google Cloud, Microsoft Azure, AssemblyAI, ElevenLabs, and any service that copies the OpenAI transcription API. Each one has a setup guide on the website.
  • **More cloud text recognition:** Microsoft Azure AI Vision and Mistral OCR. For the same company, one key is shared between speech recognition, text recognition and My AI models.
  • **Two more on-device speech models** (experimental): Paraformer and Qwen3-ASR.
  • **Quiet speech:** local models read soft recordings after noise reduction, when a steady room noise is close to the voice.
  • Vocabulary packs, text tidying, AI polish, and "My AI models" for polishing and translation.
  • Full list: [CHANGELOG.md](https://github.com/DragonKingIO/Cadenza-voice/blob/v1.2.0/cadenza/CHANGELOG.md)
  • 1. Download `Cadenza-1.2.0-macos-universal.dmg`, open it and drag Cadenza to Applications. (The zip `Cadenza-1.2.0-macos-universal.zip` holds the same app, for people who prefer it.)
  • 2. Open Cadenza from Applications. macOS blocks the first launch because the app is **not notarized**: open **System Settings → Privacy & Security**, scroll to the message about the app and choose **Open Anyway**.
  • 3. Allow Microphone, Accessibility and Input Monitoring when asked (Screen & System Audio Recording only if you use screenshots).
  • Requires macOS 14 or later, on an Apple silicon or Intel Mac.

Good to know

System
macOS 14 or later
Chip
Apple silicon or Intel
Models
Not bundled. You download them in the app, each verified with a checksum. The recommended one is about 164 MB.
Network
Only when you download a model, use a cloud service, or check for updates.
Notarization
Not notarized. macOS asks you to choose Open Anyway the first time.
Build from source

You need the Xcode Command Line Tools (xcode-select --install).

git clone https://github.com/DragonKingIO/Cadenza-voice.git
cd Cadenza-voice
./cadenza/tools/fetch-sherpa-onnx.sh     # optional: the library for local models
./cadenza/build.sh --stage-only          # creates cadenza/build/stage.noindex/Cadenza.app.zip

Unzip the result and open the app. Installation guide

Updates

Cadenza can tell you when a new version is out. Open Settings → About and press Check for updates, or let it check once a week: it asks you once during setup, and you can change your mind any time. It only reads GitHub's public release information. When there is a new version, the menu bar menu and the About page say so and link to the release page. Nothing is downloaded or installed for you.