Frequently asked questions

Most people are set up in a few minutes: download and install, grant microphone permissions, set your hotkey (Option+Space on Mac, Ctrl+Space on Windows, or your own), then try a built-in context like Email or Slack.

You can create custom contexts later. The defaults get you productive right away.

No. Download, install, and start using the built-in contexts. Cloud and Bring your own key modes need no technical configuration.

Local, on-device processing is available on Pro and Pro Plus and involves a bit more setup, but it is optional.

A few options: use a microphone close to your mouth so you can speak quietly, step away briefly for longer dictation, or use it in a private space such as a home office or car.

Starting with short dictations is also a good way to get comfortable before using it for longer messages.

It depends on the processing mode you choose. Local, on-device processing (Pro and Pro Plus) keeps audio on your machine. Bring your own key sends audio directly to the provider you connect, such as Deepgram or your chosen AI provider, via their API. Cloud, the default mode, processes audio through the Contextli backend.

Three modes: Cloud, the default, which is the simplest to set up. Bring your own key, where you connect your own provider account and pay them directly. Local, fully on-device, available on Pro and Pro Plus plans.

You can switch modes in Settings at any time.

Local mode keeps processing entirely on your device, which is the strictest option for sensitive work. We are not a covered entity and do not offer a signed BAA, so for regulated work such as healthcare, check with your own compliance team on whether Local mode meets your specific requirements.

Transcripts are stored locally on your computer in the app’s data folder, and you can view, export or delete them at any time.

Yes. Bring your own key mode supports Deepgram for transcription, and OpenAI or Anthropic for AI processing. You pay those providers directly.

Contextli has desktop apps for Mac and Windows, and mobile apps for iPhone and Android.

For Cloud and Bring your own key modes, any modern computer works fine. For Local, on-device processing, more RAM and, on Windows, a capable GPU will generally perform better; Apple Silicon Macs are well suited to on-device processing.

Auto-paste is on by default. Once Contextli finishes formatting your speech, it pastes the result into whatever text field is active, so you don’t need to copy it yourself. You can turn this off in Settings if you prefer to copy manually.

Yes. Any microphone your computer recognizes, including Bluetooth headsets and AirPods, works with Contextli. Select your preferred input in Settings.

Yes, streaming transcription is available (Deepgram or Groq, depending on your setup) so words appear as you speak.

Every plan includes a 7-day free trial. Prices start from $45 a year. Higher tiers add Local, on-device processing and more devices. See the current plan details and exact pricing on the pricing page.

Every plan starts with a 7-day free trial. A card is required to start the trial, and you can cancel any time before it ends.

Open Contextli on your Mac, Windows PC or phone, go to Settings, then Billing, and you can cancel, switch between monthly and annual billing, or update your card.

If you subscribed through the App Store on iPhone, manage it under Subscriptions in your Apple ID settings. If you paid with a different email than the one you sign in with, contact support and we will sort it out.

Contact support

If Contextli doesn’t work for you, contact us within 14 days for a refund.

Credits are the unit for cloud processing. Cloud transcription and cloud AI actions consume credits based on usage. Bring your own key and Local modes use your own keys or on-device processing instead, so they do not consume Contextli credits.

Yes, contact us for volume licensing and enterprise deployment options.

Contexts are the core feature that makes Contextli different from plain dictation. Instead of raw transcription, each context transforms your speech for a specific destination: Email context writes a professional email, Slack context writes a short casual message, and so on. Contextli ships with 18 built-in contexts, and you can create unlimited custom ones.

Yes. A custom context defines how your speech should be transformed with a prompt you write, for example "format as meeting notes" or "write code review comments." Each context can have its own hotkey.

A small on-screen control that lets you switch between contexts and see recording status without switching apps. It stays out of the way until you need it.

Contexts can be exported and imported, so you can share a context that works well for your team’s formats, for example a standard bug report or status update structure.

It’s well suited to writing about code: PR descriptions, commit messages, code review comments and documentation. It is not designed for dictating code syntax itself.

Contextli works at the system level rather than through app-specific integrations. If you can type into a text field, you can dictate into it: press your hotkey, speak, and the formatted text is pasted at your cursor.

An AI chat tool means opening a tab, typing or speaking a prompt, waiting for a response, copying the output, switching to your destination app, and pasting. Contextli’s flow is press your hotkey, speak, and the formatted output appears at your cursor, in whatever app you are already in.

Built-in dictation gives you a transcription of exactly what you said, filler words and false starts included, which then needs editing. Contextli transforms your speech for the destination context, so the output is closer to what you meant to send.