Launched this week
ora
Your personal simultaneous interpreter, on your Mac
50 followers
Your personal simultaneous interpreter, on your Mac
50 followers
Simultaneous interpreters used to be reserved for heads of state. Ora puts one on your Mac. Speak any language, see live translations stream into a floating caption card — entirely on Apple Silicon. No cloud. No account. Free forever.
Products used by ora
Explore the tech stack and tools that power ora. See what products ora uses for development, design, marketing, analytics, and more.
Design & Creative 1
Design & Creative 1
SwiftUI AppsA collection of apps built in SwiftUI
4.8 (23 reviews)
Ora is pure SwiftUI — menu-bar extra, floating caption card, Preferences window, and the iOS companion. SwiftUI Apps is the fastest way to calibrate on the visual language and motion patterns the best native Mac apps converge on, without reinventing those conventions from scratch. For a small team shipping a polished menu-bar app, a curated reference like this is disproportionately valuable.
LLMs 2
LLMs 2
OllamaThe easiest way to run large language models locally
5.0 (30 reviews)
Ora's open-source Python reference CLI uses Ollama as the translator runtime. One-line install, a clean HTTP streaming API, and a broad model catalog made it the lowest-friction way for contributors to reproduce the pipeline without MLX or Metal setup. It also powers the reference CLI's quality-tier system (Standard / High / Extra High), exposed via a single --quality flag.
Hugging FaceThe AI community building the future.
4.9 (72 reviews)
Every on-device model Ora uses — ASR and the translator LLM — is pulled from Hugging Face on first launch. The Swift-native HFHub downloader and swift-transformers library made it trivial to ship a weights-free binary that fetches what it needs at runtime, with tokenizer configs properly versioned alongside the weights. No competing registry matches that combination of coverage and Swift ergonomics.
Engineering & Development 1
Engineering & Development 1
Claude CodeAnthropic’s deep-context AI coder
5.0 (395 reviews)
Ora's macOS app, iOS companion, Python CLI, and even this launch kit were all built with Claude Code. Terminal-native and agent-first — it executes end-to-end tasks (refactoring, building, codesigning, notarizing, pushing releases) rather than just suggesting code in an editor. For a solo dev shipping a native app across three platforms in a few weeks, that autonomy was the difference between launching and not.
General 1
General 1
AppleThink Different
4.9 (55 reviews)
Every inference stage in Ora — VAD, speech recognition, and the translator LLM — runs on MLX Swift. Native Metal acceleration on Apple Silicon is what makes sub-second, on-device streaming translation realistic. Swift-native inference also means no embedded Python runtime and zero bridging overhead between the UI and the models — a cleaner path than any llama.cpp or PyTorch-based alternative I tried.