---
title: "We turned EmbeddingGemma 2 into a speech-to-text model"
slug: we-turned-embeddinggemma-2-into-a-speech-to-text-model
url: https://listedarticles.com/articles/we-turned-embeddinggemma-2-into-a-speech-to-text-model
canonical_url: https://eg2.haku.sh/
content_type: blog_post
language: en
published_at: 2026-10-13T00:00:00.000Z
updated_at: 2026-10-14T02:16:56.423Z
author: "haku"
authored_by: human
publisher: "haku.sh"
publisher_url: https://eg2.haku.sh/
topics: ["AI", "Machine Learning", "Hardware", "Open Source"]
license: all-rights-reserved
word_count: 339
reading_minutes: 1
citation: "haku, haku.sh. \"We turned EmbeddingGemma 2 into a speech-to-text model.\" 13 Oct 2026. https://eg2.haku.sh/ (all-rights-reserved)"
# The full text follows. The web page shows an extract and sends readers
# to the source above; quote the citation and link the canonical URL.
---

# We turned EmbeddingGemma 2 into a speech-to-text model

> Google's EmbeddingGemma 2 is a multimodal embedding model; this write-up shows how a small trained reader turns its audio encoder into on-device speech-to-text—about an hour of audio in ~13 seconds on a base MacBook Air—without retraining the base model for ASR.

# Embedding Gemma Transcribe

Google's EmbeddingGemma 2 is an embedding model. We turned it into a speech-to-text model:
    *an hour of audio in about 13 seconds on a base MacBook Air*, entirely on device.

models download on first launch (715 MB)

## Can an embedding model transcribe speech?

EmbeddingGemma 2 is a multimodal embedding model: text, images, audio and video in one shared space. Say a word out loud and its audio lands close to the written word.

So we tried reading words straight out of that space.

## How it works

1. EmbeddingGemma 2's audio encoder stays exactly as it is.
2. A small reader moves each short slice of audio into the model's text space.
3. The closest of ~229,000 English words wins, and the slices become a transcript.
4. A tiny extra model adds punctuation and capitals.

Only the reader is trained: under two hours on 8×H100, on openly licensed English speech. The base model was never trained for speech-to-text.

## How fast?

| Model | Runs on | Mac | Speed | 
|---|---|---|---|
| Embedding Gemma Transcribe | Neural Engine | base M3 MacBook Air, 8 GB | 288×1 hour in 12.6 s | 
| IBM Granite Speech 5.0 TurboCTC | GPU (MLX) | base M3 MacBook Air, 8 GB | ~150×1 hour in 25.7 s | 
| NVIDIA Parakeet TDT 0.6B v3 (FluidAudio) | Neural Engine | M4 Pro | 156× | 
| NVIDIA Parakeet TDT 0.6B v3 (FluidAudio) | Neural Engine | M5 Pro | 335× | 
| Phonon-2, a Parakeet v3 fine-tune (FluidAudio) | Neural Engine | M5 Pro | 480× | 

× real time: seconds of audio per second of processing. Rows 1–2: our tests on the same base M3 MacBook Air. Rows 3–5: FluidAudio's published benchmarks on larger, newer Macs and different audio. A rough guide, not a like-for-like ranking.

## Where it stands

Its word error rate is about 5% right now, against 2–3% for leading speech models. We believe a better-trained reader can close that gap; that's the next iteration.

## Use it

Drop in an audio file, or hold Right Option, speak and release to dictate into any app. It runs on the Mac's Neural Engine; your audio never leaves the machine.