YOU ARE VIEWING ONE ITEM FROM THE AICRIER FEED

Sotto debuts as an open-source, local-first macOS dictation tool powered by Whisper and Apple Silicon MLX models.

AICrier tracks AI developer news across Product Hunt, GitHub, Hacker News, YouTube, X, arXiv, and more. This page keeps the article you opened front and center while giving you a path into the live feed.

// WHAT AICRIER DOES

7+

TRACKED FEEDS

24/7

SCRAPED FEED

Short summaries, external links, screenshots, relevance scoring, tags, and featured picks for AI builders.

Sotto debuts as an open-source, local-first macOS dictation tool powered by Whisper and Apple Silicon MLX models.
OPEN LINK ↗
// 1h agoOPENSOURCE RELEASE

Sotto debuts as an open-source, local-first macOS dictation tool powered by Whisper and Apple Silicon MLX models.

Sotto is an open-source, local-first dictation application for macOS that transcribes speech directly into active text fields upon releasing a push-to-talk hotkey. Built around a decoupled architecture, the tool pairs a native Swift menu bar client with a Bun-compiled TypeScript and Fastify inference server that orchestrates Whisper for speech recognition and MLX-accelerated language models for automatic punctuation and text cleanup. The application runs completely offline on Apple Silicon Macs while also supporting remote inference on separate Mac or Linux machines. Showcased by developer Ben Davis to explore how AI coding agents enable multi-language systems development, Sotto delivers a privacy-respecting, subscription-free alternative to proprietary voice-to-text utilities.

// ANALYSIS

Local-first AI dictation tools demonstrate that combining on-device Whisper with lightweight LLM post-processing provides a faster, privacy-preserving alternative to SaaS subscriptions while illustrating the real-world power of agent-assisted polyglot development.

  • Privacy and zero recurring cost: Transcriptions and audio recordings never leave the local environment, offering an offline-ready alternative to subscription-based dictation tools.
  • Flexible client-server architecture: Decoupling the native Swift macOS interface from the Fastify model server allows users to either run self-contained locally or offload inference to a remote GPU server or Linux box.
  • Contextual LLM post-processing: Pairing an MLX text model with Whisper ensures raw speech is intelligently punctuated, cleaned, and properly formatted before being typed into active applications.
  • Practical polyglot agent workflow: Serves as a compelling case study of using AI coding agents to comfortably bridge Swift, TypeScript, Bun, Metal, and MLX into a cohesive native product.
// TAGS
sttwhispermlxmacosopen-sourcelocal-firstai-dictationswiftbun

DISCOVERED

1h ago

2026-09-19

PUBLISHED

1h ago

2026-09-19

RELEVANCE

8/ 10

AUTHOR

Ben Davis