cd /news/artificial-intelligence/a-on-device-stt-wisper-flow-alternat… · home › topics › artificial-intelligence › article
[ARTICLE · art-173433] src=github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

A on device STT Wisper Flow alternative that uses Mistral Voxtral model and AFM

An open-source macOS dictation app called Whistral offers a fully local alternative to Wispr Flow, running Mistral's Voxtral Mini 4B Realtime speech model on-device via MLX and using Apple's on-device Foundation Model for smart correction. The app requires an Apple Silicon Mac (M1 or later) running macOS 27.2 or newer and about 3.9 GB of free disk space for the model, and it supports 13 languages. On one Apple M5 machine with 16 GB of unified memory running the default 6-bit model, the first partial text appeared about 0.7 seconds after speech started and dictation finalized about 0.6 seconds after the user stopped speaking, per the project's local benchmark.

key takeaway

Whistral streams 16 kHz mono audio from a Swift AVAudioEngine app to a Python sidecar wrapping voxmlx, which emits NDJSON partial, segment and final events, and on an M5 with 16 GB of memory the first partial text appeared about 0.7 s after speech started with finalization about 0.6 s after speech s

read5 min views7 publishedNov 20, 2026
A on device STT Wisper Flow alternative that uses Mistral Voxtral model and AFM
Image: Michielbdejong (auto-discovered)

An open-source, fully local alternative to Wispr Flow for macOS. Hold a shortcut, speak, release — your words are typed into whatever app you're using. Powered by Mistral's Voxtral Mini 4B Realtime speech model running on-device via MLX. No audio, text, or telemetry ever leaves your Mac.

  • Push-to-talk or toggle dictation — a global shortcut (default ⌥Space) works system-wide, in any app.

  • Multilingual Smart Correction & Cross-Sentence Resolution — uses Apple's on-device Foundation Model to eliminate fillers (uh ,um ,like /äh ,ähm /eh ,este /يعني ), accurately resolve cross-sentence self-corrections (e.g."meet at 10, sorry I meant 11am" →"meet at 11am" ,"Können wir uns morgen treffen? Nein warte, übermorgen" →"Können wir uns übermorgen treffen?" ), while preserving real intent (apologies, additions, and intentional phrasing).

  • Speed vs. Quality presets — choose between Speed (Fast) and Quality (Accurate) for both speech recognition lookahead and LLM post-processing.

  • In-app update checking — automatically detects new releases via GitHub Releases in the background, surfacing a one-click download button in the menu bar and Settings.

  • Completely local & private — speech recognition (Voxtral on MLX) and smart correction (Apple Foundation Model) run 100% on your Mac; audio is never uploaded.

  • Apple HIG-native borderless HUD — a lightweight, non-intrusive floating overlay near your cursor shows live audio levels and streaming text using native macOS materials, typography, and standard system controls.

  • 13 languages — Voxtral's multilingual ASR and the smart corrector seamlessly process English, German, Spanish, French, Italian, Portuguese, Arabic, Dutch, Korean, Japanese, Russian, Chinese, and Turkish.

  • Smart insert — transcribed text lands in the focused text field via a paste that briefly borrows, then restores, your clipboard; a synthetic keystroke mode is available for apps that dislike synthetic pastes.

  • Native & unobtrusive — a menu-bar app that follows Apple's Human Interface Guidelines: non-activating panels, passive status feedback, proper permissions flow with purpose strings.

  • Apple Silicon Mac (M1 or later), macOS 27.2 or newer

  • ~3.9 GB free disk space for the model (downloaded once, on your first run)

Measured on one Apple M5 machine with 16 GB of unified memory, running the default 6-bit model; numbers come from a local benchmark, so treat them as a single data point rather than a promise. The first partial text appears about 0.7 s after speech starts (the first session of a run takes up to about 0.9 s to warm up), and dictation finalizes about 0.6 s after you stop speaking. The model loads in about 1 s once cached — a first-ever launch downloads the ~3.9 GB model first. To rerun the benchmark yourself, see Tests/perf-report.md and python3 Tests/bench_latency.py.

Clone this repository. 2. Open Whistral.xcodeproj in Xcode and pressRun , or build from the command line:

xcodebuild -project Whistral.xcodeproj -scheme Whistral \
  -configuration Debug -destination "platform=macOS,arch=arm64" build

On first launch, Whistral walks you through onboarding: microphone permission, Accessibility permission (for the global shortcut and text insertion), engine setup, and the model download.

  • The Swift app captures microphone audio with AVAudioEngine , converts it to 16 kHz mono, and streams it to a smallPython sidecar (Whistral/Resources/Engine/whistral_engine.py ) over a length-prefixed stdin/stdout protocol.

  • The sidecar wraps voxmlx , an MLX implementation of the streaming Voxtral pipeline, and emits NDJSON events (partial ,segment ,final ) back to Swift.

  • If Smart Correction is enabled, the final Voxtral transcript is piped to Apple's on-device Foundation Model (FoundationModels framework). The model removes spoken disfluencies, filler words, and resolves self-corrections (e.g.,"10am, sorry I meant 11am" →"11am" ). The model session is prewarmed in the background while you speak for minimal turn-around latency.

  • The HUD is a non-activating NSPanel , so your keystrokes and focus are never stolen. Text insertion is a synthetic ⌘V that saves and restores your clipboard.

  • The full sidecar protocol (framing, commands, events) is documented in docs/engine-protocol.md .

  • Audio is recorded only while the shortcut is held (or dictation is toggled on) and stays in memory.

  • The model weights and the embedded Python engine are stored locally under ~/Library/Application Support/Whistral/ .

  • No network calls except the one-time model download from Hugging Face and the background version check to GitHub Releases.

Setting Description
Dictation shortcut Re-recordable global hotkey (modifier + key required)
Push-to-talk / toggle Hold the key to talk, or press to start/stop
Insert at cursor Auto-insert the transcription into the focused app (on by default)
Insertion method Paste (fast, restores your clipboard) or synthetic keystrokes
Smart Correction Enable/disable on-device Apple Foundation Model post-processing
Correction Mode Speed (Fast, prewarmed session) or Quality (deeper cross-sentence context)
Correction Style Clean (fillers & corrections only), Natural (default: fixes grammar), Polished
Recognition Preset Speed (240 ms), Medium (480 ms default), Quality (720 ms), or Custom
Transcription delay Fine-tune streaming lookahead delay (80 ms–2400 ms)
Updates Automatic background update checking and manual Check for Updates
Sound feedback Subtle system sounds when dictation starts and finishes
Cancel with Esc Hardwired: pressing Esc cancels the current dictation
Model Voxtral Mini 4B Realtime — 6-bit (default) or BF16 (original)
Launch at login Register with SMAppService
  • Tests/test_engine_e2e.py drives the sidecar protocol end-to-end: load → start → feed audio → stop, printing every engine event.
  • The UI is built to follow Apple's Human Interface Guidelines — menu bar behavior, privacy and permission flow, onboarding, and accessibility — per HIG .
  • The app icon (also used as the logo mark above) is authored as an Icon Composer .icon document with light, dark, and tinted variants — in light and dark appearance it is a flat seven-bar waveform (amber → red) on a dark background, and the tinted variant renders the bars as monochrome glyphs; the roundedsystem squircle silhouette, corner rounding, and drop shadow you see are applied by macOS itself — the source layers are full-bleed squares.

Apache License 2.0 — see LICENSE. The model weights carry their own license from mistralai (Apache 2.0); the quantized MLX community port follows the same license.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @whistral 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/a-on-device-stt-wisp…] indexed:0 read:5min 2026-11-20 · —