On-Device Speech to Text
A locally-executing speech-to-text engine for Mac and Windows laptops that runs on about one CPU core plus the device's neural engine or GPU and roughly 800MB of memory, sending no audio over a network and claiming accuracy within 5% of the cloud API.
Find alternatives to On-Device Speech to Text
What it does
- Speech to text
Features 4
- Local transcriptionRuns speech-to-text locally on Mac, Windows and other devices so audio never leaves the machine.
- Speaker diarization and IDFull speaker diarization and identification included in the on-device engine.
- CoreML & DirectML optimizationOptimized for CoreML and DirectML so it runs on laptop hardware.
- Offline operationWorks with no network required, such as when Wi-Fi drops, for clinical and legal environments.
Sources
- Pricing
-
Official documentation · 5 Sep 2026
Quote-only; verified the self-serve pricing page carries no on-device line.
- Description
-
Official documentation · 5 Sep 2026
Page title 'On-Device Speech-to-Text for Laptop'; H1 'Speech-to-Text optimized for laptop'. States macOS 14 Sonoma+ (M1 or newer) and Windows 11 (Intel/AMD/ARM, 2GB VRAM min), '~800MB of system memory', 'within 5% of cloud accuracy', full speaker diarization and ID, CoreML/DirectML optimization, and an Adobe Premiere deployment.
- Sold within
-
Live re-check 2026-09-15: the two candidate pages contradict each other — one implies a separately-licensed product, the other frames on-device as just one deployment mode of the same underlying API.
- Modalities
-
Official documentation · 1 Oct 2026
Page: 'audio that never leaves the machine / Offload transcription from cloud to the device'.
- Intended for
-
Targets 'leading ISVs building privacy-first, laptop-native applications'; 'Enterprise' tier custom deployment; 'Government & Law Enforcement' named use case
Also from Speechmatics
-
Speech to Text API API service
Speechmatics' automatic speech recognition API transcribes audio into text in 55+ languages in either real-time streaming or batch mode, with speaker diarization, custom dictionary, translation and summarization options.
-
Text to Speech API service
Speechmatics' text-to-speech API generates streaming synthetic English speech from text with sub-150ms latency using four named voices (Sarah, Theo, Megan, Jack), aimed at real-time voice agent use.
-
Agent STT API service
Agent STT, Speechmatics' speech-to-text API for AI voice agents: final transcripts in 350ms, speaker focus and diarization, a custom dictionary and 55+ languages, with LiveKit, Pipecat and Vapi integrations.
-
Translation API service
Translates a transcript into other languages in the same API call that produces it, for files or live audio. It is a feature switched on inside a Speech to Text request rather than a separate product; the docs file it under Speech to Text and return the translations alongside the transcript.
-
Summarization API service
Generates a short summary of an audio file in the same API call that transcribes it, as paragraphs or bullets. It is a Speech Intelligence feature enabled by adding a config block to a batch Speech to Text job, not a product bought on its own.
Open Speechmatics in the directory
Something wrong here? Send a correction — quote this product id: speechmatics-on-device-speech-to-text.