Whisper Notes Guide Hub

Whisper Models and Local Transcription Benchmarks

Compare local speech recognition models by speed, accuracy, language coverage, and Apple Silicon performance.

Every local speech model we ship or have benchmarked — what each is good at, how fast it runs on Apple Silicon, and which one to pick for your language. All numbers below come from our published benchmark articles.

3 topic clusters10 guides and comparisons

Local Speech Models at a Glance (2026)

The short version: on a Mac, use Parakeet V3 for English and European languages (it's the default in Whisper Notes), SenseVoice for Chinese, Japanese, Korean, and Cantonese, and Whisper Large-v3 Turbo for everything else in its ~100-language long tail.

ModelBest forAccuracySpeed on Apple SiliconLanguagesIn Whisper Notes
Parakeet V3 (NVIDIA, 0.6B)English & European languages6.32% English WER (our FLEURS test)~10× faster than Whisper Turbo25Yes — default on Mac
Whisper Large-v3 Turbo (OpenAI, 809M)Widest language coverage7.83% English WER (our FLEURS test)~5× faster than Large V3~100Yes — optional download (~1.6 GB)
SenseVoice Small (FunAudioLLM)Chinese, Japanese, Korean, CantonesePurpose-built for CJK27-min Chinese podcast in 13.83 s (M4 Pro)CJK focusYes — since v1.5.0
Whisper Large V3 (OpenAI, 1.55B)Reference baselineNear-identical to TurboBaseline (slowest here)~100No — Turbo supersedes it
Voxtral (Mistral)Speech + language understandingSee our benchmark articleServer-class modelsMultilingualNo — covered in blog

WER = word error rate; lower is better. Our numbers: FLEURS benchmark plus in-house tests on an M4 Pro running Whisper Notes — full methodology in the linked benchmark articles below. All models listed as "in Whisper Notes" are included in the one-time price.

4

Highest-traffic model benchmarks

Start here when the searcher is comparing local ASR model speed, decoder layers, silence hallucinations, and Apple Silicon performance.

3

Model-specific local transcription pages

These pages connect model searches to practical Mac, iPhone, and multilingual transcription workflows.

3

Use models in real workflows

Where these models actually get used: iPhone recording, Mac Fn-key dictation, and end-to-end offline transcription workflows.

3

More Guide Hubs

Explore the other Whisper Notes topic hubs for models, alternatives, offline workflows, and Mac dictation.