Frequently asked questions.

InkSpoke is a cross-platform desktop Voice OS that converts speech to formatted, context-aware text and injects it directly into any active application. It works offline-first with optional cloud LLM support for enhanced refinement.

InkSpoke runs on macOS (Apple Silicon), Windows (x64), and Linux (x64). Each platform uses native APIs for optimal performance — CoreML on macOS, CUDA on Windows, and ONNX Runtime on Linux.

Yes. InkSpoke is offline-first by design. Speech recognition uses local Whisper models and text refinement can run entirely on-device via LlamaSharp. No internet connection is required for core functionality.

InkSpoke offers a free tier with core speech-to-text and basic refinement. The Pro plan unlocks advanced features like workspaces, cross-device sync, custom vocabulary, and priority support.

BYOK lets you connect your own API keys from providers like OpenAI, Anthropic, or Google. This gives you full control over which LLM models are used for text refinement, with no markup on API costs.

Your audio and text data stay on your device by default. When using cloud LLM providers, data is sent directly to the provider — InkSpoke never stores or processes your content on our servers. All credentials are stored in your OS keychain.

InkSpoke supports 99+ languages for speech recognition via Whisper. LLM refinement quality varies by language but works well with all major languages. Custom vocabulary support helps with domain-specific terms.

The Keyboard Extension lets you trigger voice input from any text field using a configurable hotkey. Press the hotkey, speak, and your refined text is automatically injected into the active application — no copy-paste needed.

Yes. InkSpoke works with any application that accepts text input, including VS Code, JetBrains IDEs, Xcode, and terminal emulators. Workspace-aware context helps produce code-appropriate output.

Download InkSpoke for your platform, install it, and press the default hotkey (Ctrl+Shift+Space on Windows/Linux, Cmd+Shift+Space on macOS) to start dictating. The onboarding wizard walks you through setup in under a minute.