Free
$0Free plan available.
VoiceInk is an open-source voice-to-text application for macOS that provides near-instant, highly accurate transcription. By utilizing local AI models, it enables offline functionality and ensures data privacy, keeping all information stored on your device with optional AI enhancement features.
1. Download and install VoiceInk on your macOS device. 2. Configure the global shortcuts to start and stop recording. 3. Speak into your microphone to have VoiceInk transcribe your speech into text. 4. Paste the transcribed text into any application.
VoiceInk uses local AI models for transcription, allowing you to work without an internet connection. All data remains stored locally on your device, and no information is transmitted unless you choose to enable AI enhancement.
Yes, the VoiceInk source code is available on GitHub. This transparency allows you to review how the application functions, contribute to community improvements, and verify that the app prioritizes your privacy.
VoiceInk is available as a one-time purchase. There are no subscriptions or recurring fees; you pay once and own the software.
Free plan available.
Use these comparison pages to understand the trade-offs between the models most relevant to VoiceInk.
Compare Gemini 1.0 Pro Deprecated and Gemini 2.0 Flash across pricing, context window, capabilities, benchmarks, and API access to choose the better fit for long-context workloads versus long-context workloads.
Compare Gemini 2.0 Flash Lite and Gemini 2.0 Flash across pricing, context window, capabilities, benchmarks, and API access to choose the better fit for long-context workloads versus long-context workloads.
Compare Gemini 1.0 Pro Deprecated and Gemini 1.5 Flash Deprecated across pricing, context window, capabilities, benchmarks, and API access to choose the better fit for long-context workloads versus general-purpose AI workloads.
Compare Gemini 1.0 Pro Deprecated and Gemini 1.5 Flash Vision Deprecated across pricing, context window, capabilities, benchmarks, and API access to choose the better fit for long-context workloads versus general-purpose AI workloads.