Overview
Local-first push-to-talk speech-to-text for developers. Press a hotkey, speak, the words land where your cursor is. Runs Whisper offline — no cloud, no telemetry.
Pricing
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Developers use SpeakCLI to dictate speech into any focused text field, such as a terminal, IDE, or browser.
- Developers use voice macros to map spoken phrases to commands or text, with exact match or regex.
- Teams use code mode to dictate text that is lowercased and stripped of spoken punctuation for pasting into a terminal.
- Developers use the CLI-aware dictionary to teach SpeakCLI command names like kubectl, terraform, and npx.
- Users dictate in any of about 99 languages to get text back in that language, or enable Translate mode to get English text instead.
- Users sync macros, dictionary, and theme across their devices with end-to-end encryption.
Features
Productivity workflow
Team operations
Data or task automation
Reviews
No reviews yet. Be the first to share your experience!
FAQ
Does my audio go to a server?
No. SpeakCLI bundles a whisper.cpp build and runs it locally on your CPU, so audio never leaves your device. The transcribed text also doesn't leave, as it is typed into the foreground window directly via the OS keyboard API.
Windows says 'Unknown publisher' / SmartScreen blocked the installer. Is this safe?
Yes, this is expected for v1. Click 'More info' → 'Run anyway' to install. The warning appears because the installer isn't code-signed yet, and code-signing will be added once revenue justifies it.
My antivirus flagged the installer. Is it malware?
No. SpeakCLI uses OS APIs that overlap with what malware also uses — microphone access, a global hotkey listener, and simulated keyboard input — which combined with an unsigned binary can trigger heuristic flags in a few niche engines.
Why not a subscription?
The site explains that subscriptions buy cloud sync and recurring features, and if the product is local-first, the subscription is just rent. It prefers a fair one-time price with future revenue from upgrades.
What's the device limit?
A Pro license activates on up to 2 devices simultaneously, and you can deactivate from any device to free a slot. Free downloads are unlimited with no account or activation required.
Can I get a refund?
Yes, within 14 days, no questions asked. Email support@speakcli.dev with your Polar order ID and the refund will be processed through Polar within one business day.
When will macOS be supported?
macOS is on the roadmap but not committed to a date. It requires an Apple Developer account and a build pipeline plus notarization workflow, though the codebase is mostly portable.