Specifications
Size
0 MB (System Built-in)
Architecture
Apple Speech Recognizer API
Latency
Minimal (<50ms processing overhead)
Language
System Speech Language
Developer / Creator
Apple Inc.
Download Source
Verified Repository Source
Pre-installed in macOS system library (no download needed)
Model Overview
Apple Speech is the default, zero-configuration transcription engine in tapWhisper. It runs 100% on-device using Apple's native Speech framework. It offers near-zero setup friction, utilizes minimum system RAM, and is highly optimized for Apple Silicon (M1/M2/M3/M4) and Intel chips. Since it uses macOS system APIs, it does not require downloading model files and is ready instantly.
Available Model Variants
| Model Name | File Size | RAM Usage | Format/Quant | Languages | Description |
|---|---|---|---|---|---|
| Apple Speech | 0 MB | 0 MB | Native API | System Speech Language | Pre-installed native macOS speech recognition path. Lowest overhead. |