Apple quietly shipped everything you need to build a real-time translator — so I built one

Description and use

Wakaru is a macOS app that turns any audio playing on your Mac into live translated subtitles, 100% on‑device, without sending data to the cloud.

Problem

Need real‑time, on‑device subtitles for confidential meetings on macOS without sending audio to the cloud.

Outcome

Wakaru delivers live, on‑device subtitles for any audio on macOS 26+, achieving near‑real‑time latency, 10 source languages, 22 target languages, and optional high‑accuracy LLM mode, all with zero external dependencies.

Workflow

• Capture system audio at 16 kHz via ScreenCaptureKit
• Use SpeechAnalyzer with .fastResults and prepareToAnalyze for low latency
• Collect complete sentences, then translate with Translation framework or Apple Intelligence LLM
• Render subtitles on a transparent NSPanel overlay
• Handle sample rate, reporting cadence, lazy loading, and shutdown optimizations
• Use content anchors to avoid re‑translation of rewritten text
• Manage TranslationSession via invisible .translationTask in SwiftUI
• Implement LLM guardrails: 2.5 s deadline, session reset every 10 sentences, reject degenerate output

Evidence

Wakaru runs on macOS 26+ (Apple silicon). It's free for 14 days (and stays free for 1 hour/day after that), with a one-time purchase for unlimited time — no subscription

Source

SpeechAnalyzer prefers 16 kHz audio. My first version captured at 48 kHz and resampled with AVAudioConverter — and the first caption took seconds to appear.

Source

Translation framework only works inside SwiftUI .translationTask view modifier.

Source