Speech to text where local or cloud depends

“When you use Dictation, your device will indicate in Keyboard Settings if your audio and transcripts are processed on your device and not sent to Apple servers.”

apple.com

“Otherwise, the things you dictate are sent to and processed on the server, but will not be stored unless you opt in to Improve Siri and Dictation.”

apple.com

“Cloud dictation needs an internet connection. Offline availability varies by platform, app version, and mode; contact support to check what your setup supports.”

aquavoice.com

“Run on our fully managed cloud or inside your own environment.”

assemblyai.com

“This works locally (offline) on your own computer.”

brainasoft.com

“Available in real time or batch, in the cloud or self-hosted.”

deepgram.com

“After the initial transcription, Descript stores your audio, video, and transcription data on either Amazon S3 or Google Cloud, which are services trusted by thousands of other organizations that prioritize security.”

descript.com

“It only sends the speech to Google servers via Chrome over HTTPS (secure) for speech recognition and outputs the transcribed text in your browser.”

dictation.io

“No. Dictation relies on the Google speech recognition engine that transcribes your speech to text in the cloud.”

dictation.io

“Dragon Medical One is a cloud-based … speech solution for clinical documentation”

marketplace.microsoft.com

The product page and data sheet we checked do not say where v16 processes audio.

“All your data is stored and processed in the US cloud infrastructure by default.”

fireflies.ai

Google states neither on-device nor cloud. It says your browser decides:

“When you turn on voice typing or captions, your web browser controls the speech-to-text service. It determines how your speech is processed and then sends the text to Google Docs or Google Slides.”

support.google.com

“All of our services run in the cloud. We don't host or run our own routers, load balancers, DNS servers, or physical servers. Our service is built on Amazon Web Services and Heroku.”

happyscribe.com

“Process sensitive content locally without data ever leaving your Mac.”

macwhisper.com

“All transcription is done on your device, no data leaves your machine. This makes MacWhisper a great app for sensitive audio such as interviews.”

goodsnooze.gumroad.com

“Easily switch between different models hosted remotely or locally on your Mac.”

macwhisper.com

“Notta hosts all its software on Amazon Web Services (AWS), a leading infrastructure provider that provides a reliable, scalable, and secure environment for storing data in the cloud.”

notta.ai

“Data Storage: Otter uses AWS S3 storage and enables AWS SSE (Server Side Encryption) on data (S3 buckets), as well as for machine data volumes.”

otter.ai

“If you are using the desktop or mobile app for our speech recognition service, no audio or text is saved on our servers. The audio and text files simply pass through our servers.”

speechlive.com

“We employ TLS 1.2 and 1.3 for data in transit, ensuring secure communication between Rev servers and our customers. For data at rest, we use Amazon's S3 SSE (Server-Side Encryption) with unique keys for all buckets and objects.”

rev.com

“If you order human transcription with Rev, only vetted transcriptionists have access to your files.”

rev.com

“All data is stored at AWS in the USA. Sonix does not use your data to train our models. No one has access unless you provide consent.”

sonix.ai

“Sub-second latency, no infrastructure costs and audio that never leaves the machine.”

speechmatics.com

“A speech-to-text API with three ways to deploy it: cloud, on-prem, or on-device.”

speechmatics.com

“We send your audio to Google's & Microsoft's speech recognition engines for the transcription.”

speechnotes.co

“For dictation, the recording & recognition - is delegated to and done by the browser (Chrome / Edge) or operating system (Android). So, we never even have access to the recorded audio, and Edge's / Chrome's / Android's (depending the one you use) privacy policy apply here.”

speechnotes.co

“When using local models: Your audio recordings and transcriptions never leave your device. All speech-to-text processing happens entirely on your device, ensuring complete privacy of your spoken content.”

spokenly.app

“When using built-in cloud models (no API key required): Spokenly captures your voice input and sends the corresponding audio file to our backend for transcription purposes.”

spokenly.app

“It records and summarizes meetings too, and with local models nothing you say leaves your device.”

superwhisper.com

“Unlimited use of Cloud and Local AI models”

superwhisper.com

No page we checked says where audio is processed.

“Trint uses HTTPS (using TLS 1.2) for secure data upload, export and transfer. Data is encrypted at-rest using AES 256. Physically, Trint uses data centers owned and operated by Amazon Web Services (AWS) in both the EU and US.”

trint.com

“VoiceInk processes all voice transcription locally on your device. Your voice data never leaves your Mac, ensuring complete privacy.”

tryvoiceink.com

“Cloud transcription: Your audio file is sent to your selected provider for transcription”

tryvoiceink.com

“On-device voice-to-text software for Mac”

voiceprivate.com

“Works offline Dictate anywhere, anytime. No internet connection required.”

voiceprivate.com

“Dictate without an internet connection, powered entirely by your device.”

willowvoice.com

“Willow runs on secure cloud infrastructure in the United States.”

willowvoice.com

“With voice typing, you can enter text on your PC by speaking. Voice typing uses online speech recognition, which is powered by Azure Speech services.”

support.microsoft.com

“Transcription always occurs on the cloud. This is the best way for us to provide accurate, low latency transcription.”

wisprflow.ai

“Transcription always happens in the cloud to provide the best speed and accuracy.”

wisprflow.ai