Skip to main content
OpenSourceAlternatives

VoiceInk

Open source · OSI-approvedStatus: unknownNew

Local voice dictation with AI cleanup for macOS

Alternative to Wispr Flow

VoiceInk is a free, open-source voice dictation app for the Mac that turns speech into polished text anywhere you can type. You hold a shortcut, speak, and release: the app transcribes locally with Whisper and then applies an AI cleanup pass that removes filler and fixes punctuation before pasting the result.[1]

Quick verdict

Mac users who want private, subscription-free dictation get the most from VoiceInk: local Whisper transcription plus an AI cleanup pass turns speech into formatted text in any app, free of charge. The decisive tradeoff is platform and setup: it is macOS-only on Apple Silicon with local models to download, so anyone needing Windows, mobile, or zero-configuration hosted dictation should choose the Wispr Flow incumbent instead.[1][2]

Key features

  • On-device Whisper transcription On-device Whisper transcription: speech is converted to text on your Mac by a local Whisper model, so dictation audio never leaves the machine.[1][2]

  • AI-powered enhancement pass AI-powered enhancement pass: the raw transcript runs through a cleanup model that removes filler words, repairs punctuation, and formats the text before it is pasted.[1][2]

  • Dictation anywhere you type Dictation anywhere you type: the recorder works in any application, with right-click recording plus a paste or clipboard-copy choice for where the text lands.[1]

  • Custom vocabulary Custom vocabulary: names, jargon, and technical terms can be taught to the app so specialized dictation comes out spelled correctly.[1][2]

  • Power Mode dictation rules Power Mode dictation rules: per-app configurations adapt transcription and formatting to the active application, with custom prompts, model selection, and post-processing scripts for each context.[1]

  • Shortcuts, automation, and developer hooks Shortcuts, automation, and developer hooks: macOS Shortcuts actions, an MCP server for AI assistants, and an AI API for custom integrations extend dictation into scripted workflows.[1]

  • Local-first model choice Local-first model choice: transcription models download and run on-device, and the AI enhancement step supports local LLM providers such as Ollama and llama.cpp alongside cloud providers.[1]

  • Free core with one-time Power Mode Free core with one-time Power Mode: the app is free with no subscription, and the advanced Power Mode tier is a single one-time payment of $25 rather than a recurring plan.[1][2]

Who will love it

  • Privacy-conscious Mac users dictating sensitive material: on-device transcription means spoken words stay off hosted services entirely.[1][2]

  • Writers and professionals who live in many apps: per-application Power Mode rules keep formatting and vocabulary correct as focus moves between tools.[1]

  • Open-source supporters who want dictation without a subscription: the GPL-3.0 codebase and free core remove both the fee and the vendor lock-in.[1]

Who should avoid it

  • Windows, Linux, or mobile users: VoiceInk is macOS-only, so anyone outside the Mac has no supported path.[1][2]

  • Older or Intel Macs: the app targets Apple Silicon with recent macOS (site lists macOS 14.4 and later, repo README lists macOS 15.0 and later), leaving older machines behind.[1][2]

  • Users wanting a zero-setup hosted service: local models must be downloaded and advanced AI features need your own provider API keys, which is more setup than a cloud dictation subscription.[1]

Alternatives and compatibility

Wispr Flow is the incumbent in the published catalogue relationship and the honest hosted redirect: cloud processing with a free tier and $12/month Pro for users who prefer a managed service over local setup.[1]

VoiceInk's decisive difference is locality: transcription runs on-device with no account and no audio upload, which is precisely the property the catalogue's Wispr Flow description says sends privacy-conscious users looking for a local alternative.[1]

Choose VoiceInk when dictation must stay on the machine and remain free of subscriptions; choose the hosted incumbent when cross-platform support and zero local setup matter more than locality.[1][2]

Questions worth asking

What is the best VoiceInk alternative for non-technical users?

Wispr Flow, the incumbent in this catalogue relationship, is the easier pick for non-technical users because it is a polished hosted product, while VoiceInk's local-model setup and macOS-only open-source packaging assume more hands-on configuration.[1][2]

Is VoiceInk really no-code?

Yes. VoiceInk is a normal macOS app with a menu-bar interface, keyboard shortcut, and onboarding walkthrough; dictation, vocabulary, and Power Mode rules are all configured through the GUI, and only the optional advanced integrations assume developer tooling.[1][2]

How much does VoiceInk cost per month?

VoiceInk itself costs nothing per month: the core app is free with no subscription, and Power Mode is a one-time payment of $25. Optional AI enhancement through your own provider API keys carries that provider's usage charges. Checked October 9, 2026.[1][2]

Can you self-host VoiceInk?

There is nothing to host: VoiceInk is a GPL-3.0 open-source macOS app that runs entirely on your machine, and you can clone the repository and build it yourself with Xcode rather than downloading the release. Self-operation means keeping your own build working on supported macOS versions.[1]

Sources and editorial review

Source research. Reviewed on October 9, 2026. Reviewed by Sanjib Sah. Written by Sanjib Sah. AI assisted; reviewed by a human editor.

We have not run or tested this product.

  1. VoiceInk official site (tryvoiceink.com)

    official · Observed October 9, 2026

    Official VoiceInk site: free open-source mac-first positioning, on-device Whisper transcription, AI enhancement, custom vocabulary, prompt-anywhere workflow, Power Mode per-app rules with custom prompts and scripts, Shortcuts/MCP/API integrations, macOS 14.4+ on Apple Silicon, one-time $25 Power Mode pricing.

  2. VoiceInk repository README (official)

    official · Observed October 9, 2026

    Official VoiceInk GitHub repository (Beingpax/VoiceInk): local-first architecture, on-device Whisper models, enhancement via Ollama/llama.cpp or cloud providers, custom dictionary, free core with one-time Power Mode, GPL-3.0 license, Xcode build instructions, Apple Silicon and macOS 15.0+ requirement.

Compared with these products

Similar projects

Related projects with shared categories, technologies, or licensing.

Ollama

OllamaAIOpen

Run open language models locally with one command

Stars179.9K
Commit14h ago
LicenseMIT

Ollama reduced local model hosting from an afternoon of CUDA troubleshooting to a single pull command. It handles model download, quantisation selection, GPU offloading, and memory management, and exposes an OpenAI-compatible endpoint on localhost.

LocalAI

LocalAIAIOpen

Self-hosted OpenAI-compatible runtime for local AI models

Stars49.5K
Commitjust now
LicenseMIT

LocalAI is a self-hosted runtime that runs AI models locally behind OpenAI-compatible endpoints.

whisper.cpp

whisper.cppAIOpen

Speech recognition that runs anywhere, with no runtime

Stars43.2K
Commit1d ago
LicenseMIT

whisper.cpp is a C and C++ port of the Whisper speech recognition model with no Python dependency, quantised weights, and hardware acceleration across Apple Silicon, CUDA, and plain CPU.

llama.cpp

llama.cppAIOpen

Inference engine that runs LLMs on almost any hardware

Stars126.6K
Commit8h ago
LicenseMIT

llama.cpp is the layer most local model tooling is built on. It is a C and C++ inference engine with no Python runtime, aggressive quantisation support, and hand-tuned kernels for a remarkably wide range of hardware.

LiteLLM

LiteLLMAIOpen

Open-source AI gateway unifying 100+ LLMs behind one API

Stars60.1K
Commitjust now
LicenseMIT

LiteLLM is an open-source AI gateway that calls more than 100 large language model providers through one OpenAI-compatible interface.

FluidVoice

FluidVoiceAIOpen

Free open-source macOS dictation with on-device AI cleanup

Stars11.9K
Commitjust now
LicenseGPL-3.0

FluidVoice is a free macOS dictation app that transcribes speech on the machine and types polished text into any app, positioned as a local alternative to Wispr Flow.