---
format: "aidr-story-markdown/v1"
id: "2a917e1d99326803471dd1bb331acdcd0303538773183f8c7512b17ce245e36d"
canonical_url: "https://aidr.today/2a917e1d?lang=en"
title: "Tether Ships 254M Parameter AI Model for Faster On Device Speech"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-14T14:42:44.000Z"
category: "Models"
topics: ["inference"]
source_urls: ["https://huggingnews.com/ai/tether-ships-254m-parameter-ai-model-for-faster-on-device-speech-b4d0f603","https://x.com/qvac/status/2110369471802290206","https://x.com/TheBlockCo/status/2110347481783705737","https://marketbrief.now/ai/tether-ships-254m-parameter-ai-model-for-faster-on-device-speech-b4d0f603"]
summary: "Tether has released QVAC TranscribePsy, a 254 million parameter speech-to-text model that runs on local hardware to enable offline transcription on smartphones and laptops. The model supports 25 European languages on laptops and 8 languages on mobile devices, and reportedly transcribed a 10 minute recording in 1.65 seconds on an iPhone 17 Pro Max's Neural Engine. Tether's QVAC division emphasized that local processing via the parakeet engine is critical for privacy as devices shift toward voice interfaces."
---

# Tether Ships 254M Parameter AI Model for Faster On Device Speech

> [Open the canonical story](<https://aidr.today/2a917e1d?lang=en>)

**Published:** 2026-10-14T14:42:44.000Z
**Category:** Models
**Topics:** inference

## Summary

Tether has released QVAC TranscribePsy, a 254 million parameter speech\-to\-text model that runs on local hardware to enable offline transcription on smartphones and laptops\. The model supports 25 European languages on laptops and 8 languages on mobile devices, and reportedly transcribed a 10 minute recording in 1\.65 seconds on an iPhone 17 Pro Max's Neural Engine\. Tether's QVAC division emphasized that local processing via the parakeet engine is critical for privacy as devices shift toward voice interfaces\.

## Sources

- [Story source](<https://huggingnews.com/ai/tether-ships-254m-parameter-ai-model-for-faster-on-device-speech-b4d0f603>)
- [Story source](<https://x.com/qvac/status/2110369471802290206>)
- [Supporting source](<https://x.com/TheBlockCo/status/2110347481783705737>)
- [Story source](<https://marketbrief.now/ai/tether-ships-254m-parameter-ai-model-for-faster-on-device-speech-b4d0f603>)