LLMVoice vs System26

LLMVoice — iOS 26 Speech & On-Device AI Showcase A technical showcase of Apple's latest iOS 26 technologies for speech recognition and on-device AI, including MLX Swift for running open-source language models locally on Apple Silicon. Built for Developers & Early Adopters LLMVoice is made for developers and AI enthusiasts who want to explore Apple's newest frameworks and on-device AI capabilities, end to end, on a real device. What It Does • Real-time voice transcription using iOS 26 speech APIs • AI-powered summarization with multiple model options • Generated code shown with syntax highlighting • Live HTML preview for generated content, with built-in diagnostics • Optional "thinking" view: see the model's reasoning, or hide it for a clean output • Modern SwiftUI interface with smooth streaming updates • 100% on-device processing for complete privacy Key Technologies MLX Swift Framework Apple's MLX (Machine Learning Extensions) enables efficient inference of quantized language models on Apple Silicon with optimized GPU acceleration. Apple's On-Device Foundation Models On supported devices (iPhone 15 Pro or later), use Apple's built-in system models for summarization — no extra downloads required. Open-Weights Models via MLX Choose from multiple open-source models running locally: • Qwen2.5 (0.5B) — 150MB, 29+ languages, 32k context • Gemma 3 (1B) — 300MB, 140+ languages, 32k context • Llama 3.2 (1B) — 500MB, 8 languages (EN/ES/FR/DE/IT/PT/HI/TH) All models use 4-bit quantization for mobile efficiency. Token limits are tuned per model for reliable results. SpeechAnalyzer & SpeechTranscriber (iOS 26) Low-latency, real-time on-device speech recognition using Apple's newest APIs. Modern Swift & SwiftUI Built with Swift 6, the Observable macro, async/await, and actor-based concurrency. How It Works 1. Select an AI model (Apple's on-device models, or download an MLX model) 2. Tap the microphone to start recording 3. Speak naturally — real-time transcription appears 4. Tap stop when finished 5. The model generates a concise summary instantly 6. Summaries are saved locally and persist between sessions 7. Swipe to delete, tap to view the original transcription Privacy-First Everything runs on-device: • Audio never leaves your device • Local speech recognition and AI inference • No cloud processing or internet required (except model downloads) • No tracking, no data collection Requirements • iOS 26.0+ (iPadOS 26.0+ for iPad) • Apple Silicon recommended • Storage for models (150MB–500MB each) • Microphone and speech recognition permissions Good to Know • Models are downloaded on first use from Hugging Face • Apple's on-device models are available immediately on compatible devices, without downloads • Primarily optimized for English; other languages vary by model Perfect For • Developers exploring iOS 26 and MLX Swift • AI enthusiasts interested in on-device LLMs • Students learning SwiftUI and modern concurrency • Anyone curious about running open-weights models on mobile Under the Hood Demonstrates MLX Swift integration with Apple frameworks, including model downloading, GPU memory management, streaming inference with real-time metrics, and efficient on-device transformer execution. Mac Catalyst Compatible Runs on macOS 26+ with Apple Silicon for a unified cross-platform experience.

System26 is a lightweight way to see device-native AI performance on your hardware. Designed for developers and enthusiasts, it surfaces on-device AI metrics across macOS, iOS, iPadOS, and visionOS. Features: • Large Language Models: Track Tokens Per Second (TPS), Latency, and Memory usage for the native System Language Model. • Image Generation: See on-device image synthesis speed using ImagePlayground with support for animation, illustration, and sketch styles. • Computer Vision: View live camera inference performance for Object Detection, Text Recognition, and Body Pose estimation. • Thermal Monitoring: Keep an eye on your device's thermal state during intensive inference tasks. • 100% Private & Offline: System26 operates without an internet connection. No data is collected, stored, or transmitted—ever. Unlock the full potential of your hardware and see how foundation models run on your machine.