---
format: "aidr-story-markdown/v1"
id: "029be8e197ee746b005fa0f578e9efaaecff8aacd5e552983f063ee031f0ceab"
canonical_url: "https://aidr.today/029be8e1?lang=en"
title: "Reson8's New 0.5B Parameter Speech-to-Text Model Outperforms Systems 20x Its Size"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-18T15:51:40.000Z"
category: "Models"
topics: ["open-source"]
source_urls: ["https://marketbrief.now/ai/reson8s-new-05b-parameter-speech-to-text-model-outperforms-systems-20x-i-355ec231","https://huggingnews.com/ai/reson8s-new-05b-parameter-speech-to-text-model-outperforms-systems-20x-i-355ec231"]
summary: "Amsterdam startup Reson8 released Rumble-2-Flash, a 0.5B parameter speech-to-text model designed to run locally on smartphones and laptops. The 1GB model can transcribe voice notes and calls without an internet connection and outperforms transcription systems 20 times its size. The model is free under an Apache 2.0 license and supports 45 languages. It was specifically trained on audio that typically disrupts transcription tools, such as heavy accents, street noise, bad phone lines and overlapping voices."
---

# Reson8's New 0\.5B Parameter Speech\-to\-Text Model Outperforms Systems 20x Its Size

> [Open the canonical story](<https://aidr.today/029be8e1?lang=en>)

**Published:** 2026-11-18T15:51:40.000Z
**Category:** Models
**Topics:** open\-source

## Summary

Amsterdam startup Reson8 released Rumble\-2\-Flash, a 0\.5B parameter speech\-to\-text model designed to run locally on smartphones and laptops\. The 1GB model can transcribe voice notes and calls without an internet connection and outperforms transcription systems 20 times its size\. The model is free under an Apache 2\.0 license and supports 45 languages\. It was specifically trained on audio that typically disrupts transcription tools, such as heavy accents, street noise, bad phone lines and overlapping voices\.

## Sources

- [Story source](<https://marketbrief.now/ai/reson8s-new-05b-parameter-speech-to-text-model-outperforms-systems-20x-i-355ec231>)
- [Story source](<https://huggingnews.com/ai/reson8s-new-05b-parameter-speech-to-text-model-outperforms-systems-20x-i-355ec231>)

