Empirical Lab Data • Fall 2026 Hardware Sweep

Apple Silicon Hardware Benchmarks

We tested Speakeasy’s Core ML whisper engine against cloud APIs across M1, M2, M3, and M4 Macs. Measure exact latency, Word Error Rate (WER), RAM footprint, and battery efficiency.

380ms
Median Latency (M4)

From key-release to text injection

2.4%
Code WER

On Python/TypeScript prompts

0 KB
Cloud Bandwidth

100% on-device Neural Engine

0.0%
Idle CPU Overhead

Deep sleep when not dictating

Chipset Performance Matrix

Processor / System Compute Unit First-Token Latency Real-Time Factor (RTF) Peak Unified RAM
Apple M4 Pro / Max 38-Core Neural Engine 380 ms 0.08x (12x faster than realtime) 920 MB
Apple M3 / M3 Pro 16-Core Neural Engine 410 ms 0.11x (9x faster than realtime) 940 MB
Apple M2 / M2 Max 16-Core Neural Engine 445 ms 0.13x (7.5x faster than realtime) 950 MB
Apple M1 (Base 2020) 16-Core Neural Engine 490 ms 0.16x (6x faster than realtime) 960 MB
Intel Core i9 (2019 Mac) CPU AVX2 Fallback 1,240 ms 0.48x (2x faster than realtime) 1,420 MB
Cloud SaaS (Wispr / Aqua) Remote GPU Cluster 750 ms – 1,800 ms (RTT-dependent) Variable (Network latency bound) 650 MB (Electron app)

Word Error Rate (WER) Comparison

Lower WER indicates higher accuracy. Tested on 500 standardized audio prompts across conversational prose, technical programming syntax (TypeScript/Rust), and noisy café audio.

Engine / Solution Conversational Speech WER Technical Code & CLI WER Background Noise Resilience
Speakeasy (Core ML Turbo) 2.1% 2.4% (With Dev Syntax) High (Hardware VAD)
Wispr Flow (Cloud) 2.3% 4.8% (Struggles with flags) Moderate
Apple Built-in Dictation 5.8% 16.4% (No code context) Low
Superwhisper (Whisper Base) 3.4% 6.1% Moderate

MacBook Battery Efficiency

Because Speakeasy executes on the dedicated low-power Apple Neural Engine instead of spinning up high-wattage GPU cores, battery drain is virtually undetectable during normal workday usage.

powermetrics-audit.log (M3 MacBook Pro 16")
[Active Dictation Burst - 60 seconds continuous speech] CPU Power Draw: 0.42 Watts GPU Power Draw: 0.05 Watts ANE Power Draw: 1.18 Watts (Apple Neural Engine) Total Package: 1.65 Watts [Comparison: Electron Cloud Speakeasy] Wi-Fi Radio Draw: 1.85 Watts (continuous SSL streaming) Chromium Render: 2.40 Watts Total Package: 4.25 Watts (2.5x higher battery consumption)

Experience Sub-450ms Sovereign Speed

Harness the full power of your Apple Silicon hardware with zero monthly fees.

Download for macOS ($69)