← Back to news30 September 2026

From 17 hours of video to a second brain: local transcription with Whisper on MLX

A well-documented experiment: 67 course videos transcribed locally and offline with whisper-large-v3-turbo rebuilt on MLX for the Mac's GPU — 17 hours of video processed in 34 minutes, without a single byte leaving the machine.

Read original article

Local voice: from Whisper to text-to-speech

How to build a fully local voice pipeline: transcription with Whisper, synthesis with Piper or Kokoro-82M, hardware requirements, and practical use cases.

Local AI on Mac: the complete Apple Silicon guide

Unified memory, Ollama in three commands and the right models for your Mac: everything you need to run local AI on Apple Silicon.

Costs: local vs API, done with real numbers

How much does local really cost compared to a cloud API? Verified per-token prices, GPU amortization, electricity and the break-even point, calculated with real numbers.

Get the next local-AI briefing

Once a week, the top selection from iaLocale: articles, news and resources on local AI, and more.

Newsletter language

I consent to the processing of my data to receive the iaLocale newsletter. Read the Privacy Policy.

After signing up you receive a confirmation email (double opt-in). Without confirmation we send nothing. No spam, we promise.

Related resources

Tools and resources from the iaLocale archive relevant to this content.

🎧

Whisper Large-v3-Turbo

Models

Il modello di trascrizione di riferimento per l'IA locale: 809M di parametri, 99 lingue, licenza MIT. Versione distillata di Large-v3 con decoder ridotto da 32 a 4 layer: trascrive circa 8 volte più veloce con perdita di accuratezza trascurabile. Gira in tempo reale su una GPU consumer e anche solo su CPU.

⚡

faster-whisper

Inference

Reimplementation of Whisper based on CTranslate2: up to 4 times faster than openai/whisper with the same accuracy and less memory. Supports 8-bit quantization on both CPU and GPU.

🎙️

whisper.cpp

Inference

Il port C/C++ ad alte prestazioni di Whisper: trascrizione vocale in locale ottimizzata per CPU e Apple Silicon, senza dipendenze da Python. Quantizzazione GGML (Q4_0–Q8_0) con riduzione fino al 65% a disco, streaming via whisper-stream, accelerazione Metal/Vulkan. MIT.

Kandinsky 6.0 Video