Gemma 4 audio with MLX

Simon Willison’s Weblog Subscribe Sponsored by: Teleport — Connect agents to your infra in seconds with Teleport Beams. Built-in identity. Zero secrets. Get early access Thanks to a tip from Rahim Nathwani, here's a uv run recipe for transcribing an audio file on macOS using the 10.28 GB Gemma 4 E2B model with MLX and mlx-vlm: uv run --python 3.13 --with mlx_vlm --with torchvision --with gradio \ mlx_vlm.generate \ --model google/gemma-4-e2b-it \ --audio file.wav \ --prompt "Transcribe this audio" \ --max-tokens 500 \ --temperature 1.0 I tried it on this 14 second .wav file and it output the following: This front here is a quick voice memo. I want to try it out with MLX VLM. Just going to see if it can be transcribed by Gemma and how that works. (That was supposed to be "This right here..." and "... how well that works" but I can hear why it misinterpreted that as "front" and "how that works".) Posted 12th April 2026 at 11:57 pm Recent articles Meta's new model is Muse Spark, and meta.ai chat has some interesting tools - 8th April 2026 Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me - 7th April 2026 The Axios supply chain attack used individually targeted social engineering - 3rd April 2026 This is a note by Simon Willison, posted on 12th April 2026. python 1243 ai 1957 generative-ai 1737 llms 1704 uv 92 mlx 42 gemma 14 speech-to-text 17 Monthly briefing Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments. Pay me to send you less! Sponsor & subscribe Disclosures Colophon © 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026