Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
Voice dictation apps
Desktop and mobile apps that turn speech into text for everyday writing.
22 projects100% active68% build on a shared standardMapped 2026-10-26
What they agree on
- Is it actively maintained? active (100% of 22)
- Do you need an account to use it? no account (70% of 20)
- Who is it for? non-developers (77% of 22)
What they argue about
How is the main thing licensed?
How is it mainly sustained?
Can it run entirely on your own device or infrastructure, without the maker's servers?
Which shared standard or format does it mainly build on?
Where does speech recognition happen by default?
Which open speech models can it run on your device?
Does it use an AI model to clean up or rewrite your dictated text, and where does that run?
If you use cloud speech or AI, how is it paid for?
What is the main way users pay the maker?
Where does it run?
Does it also record meetings or calls?
Is 'your voice never leaves your device' the headline promise?
Projects
| Project | Status | What it is |
|---|---|---|
| airtxt | Active | iPhone and iPad voice keyboard from Aistardev LLC that transcribes on device and sends text for AI cleanup, with paid Pro tiers. |
| BetterWispr | Active | Free, open-source push-to-talk dictation for Mac with local Parakeet, Whisper and Apple speech models and optional local or cloud cleanup. |
| Blurt | Active | AssemblyAI's open-source Mac dictation app that sends each utterance to AssemblyAI's API for transcription and LLM polish, using your own k… |
| Dictata | Active | Windows dictation app in Rust that runs whisper.cpp or ONNX models (Parakeet, SenseVoice, Moonshine) locally, with optional cleanup by a lo… |
| Dictámelo | Active | MIT-licensed Rust/Tauri dictation for macOS and Windows with local Whisper, Parakeet and Canary, your own cloud keys, or a free/Pro hosted… |
| Handy | Active | Free, open-source, cross-platform push-to-talk dictation that runs Whisper or Parakeet on your computer, with optional post-processing thro… |
| Kekoso | Active | Paid ($29 one-time) Mac app for on-device dictation and file, YouTube and call transcription with Parakeet, Whisper and SenseVoice models. |
| MacWhisper | Active | Good Snooze's Mac app for local Whisper/Parakeet transcription of files and meetings, with system-wide dictation; free tier plus one-time P… |
| Murmur | Active | Open-source Mac menu-bar push-to-talk dictation that sends audio to OpenAI with your own API key. |
| Plainsay | Active | 12 MB native Mac dictation app with free local Whisper and Parakeet, optional AI 'Polishing', and an optional $4/month hosted cloud. |
| ProofFlick | Active | Windows tray app that proofreads selected text and dictates via your own Deepgram or Groq key, sold for a one-time price. |
| Qwen Scribe | Active | Mac menu-bar app and local web interface that transcribes files and does push-to-talk dictation with Alibaba's open Qwen3-ASR model on Appl… |
| Sayso | Active | Free, GPL-licensed dictation app for macOS, Windows and Linux that runs Parakeet, Whisper and many other models locally, with optional AI '… |
| SpeakoFlow | Active | Free, MIT-licensed voice typing, voice assistant and meeting recorder for Windows, Mac and Linux, local by default with optional cloud keys. |
| superwhisper | Active | Commercial AI dictation app for Mac, Windows, iOS and Android with local Whisper-family and cloud models and custom AI modes. |
| TuxWhisper | Active | Offline push-to-talk dictation for Linux (X11 and Wayland) using faster-whisper, with an optional cleanup key that runs a local Ollama mode… |
| Vokalu | Active | Windows and Mac dictation and meeting-notes app run by one maker, billed per minute of cloud speech, with a free on-device 'Private mode'. |
| VoxScribe | Active | Free, MIT-licensed hold-to-talk voice typing for Windows and Android using faster-whisper on the device, with a $14 one-time Pro unlock. |
| WhisprNote | Active | Mac meeting-notes app from Attechy Ltd with on-device dictation and autocomplete, free with a Pro plan for cloud write-ups. |
| Willow | Active | Venture-style AI dictation app for Mac, Windows and iPhone from Willow Care Inc. that formats speech and learns your writing style, on a su… |
| Wispr Flow | Active | The best-known AI dictation app (Wispr AI Inc.) for Mac, Windows, iOS and Android; cloud transcription and rewriting on a subscription, and… |
| YazSes | Active | Free, offline hold-to-talk dictation for Linux (primary), macOS and Windows using faster-whisper on the CPU, with meeting capture and speak… |
Where they meet
- Handy Discord discord
Linked from the Handy README; the largest open-source project's community. - awesome-whisper awesome list
Lists dictation apps (MacWhisper, superwhisper, VoiceInk, TypeWhisper, OpenSuperWhisper, Ito); last push 2026-09-17. - Show HN forum
45+ dictation/transcription launches between 2026-07-27 and 2026-10-25; most makers here launched there, several more than once.
Follow
RSS for this community: projects added, status changes, and later polls and discussions.
Follow the whole community: OPML of every project's own release feed (where we found one) · OPML of every project's Poll Position feed.
The poll
Every project above was answered against these questions. Core questions are shared by all communities; the rest are this community's own.
- Is it actively maintained? core
active · active, but changed direction (pivot, fork, or rename) · maintenance or slowing · dormant, sunsetting, or archived - How is the main thing licensed? core
permissive open source (MIT/Apache/BSD) · copyleft or source-available with restrictions · open parts around a closed core · proprietary or closed source - How is it mainly sustained? core
individual side project, no revenue · individual with revenue (paid app, tier, ads, or donations) · community, foundation, or research · company with a paid product, tier, or ads · company or startup with a free product (no revenue yet) · big company side project - Can it run entirely on your own device or infrastructure, without the maker's servers? core
yes · yes, but it calls a third-party service you choose (your own API key or account) · partly (some features need the maker's servers) · no, it needs the maker's servers · not applicable - Do you need an account to use it? core
no account · optional account · account required - Who is it for? core
developers · non-developers · both - Is there public evidence it's built with AI coding agents? core
yes, the repo shows it (agent instruction files or agent co-authored commits) · yes, the maker says so · no public evidence - Which shared standard or format does it mainly build on? core
OpenAI Whisper models (whisper.cpp, faster-whisper, WhisperKit) · NVIDIA Parakeet models · Apple's built-in speech recognition · OpenAI's transcription API or OpenAI-compatible endpoints · none of these (its own format or interface) · not applicable - Where does speech recognition happen by default? approach
on your device by default · on device or cloud, you choose at setup · in the cloud by default, with an on-device option · in the cloud only - Which open speech models can it run on your device? approach
none (cloud only, or only its own or the system's built-in model) · one model family (e.g. only Whisper) · several model families (e.g. Whisper and Parakeet) - Does it use an AI model to clean up or rewrite your dictated text, and where does that run? value
no AI rewrite (raw text or simple rules only) · AI rewrite on your device only · AI rewrite in the cloud only · AI rewrite on device or in the cloud, your choice - If you use cloud speech or AI, how is it paid for? value
no cloud option · only with your own API key (you pay the provider) · only through the maker's cloud (free tier, subscription, or credits) · either the maker's cloud or your own key - What is the main way users pay the maker? value
nothing · a one-time purchase (or one-time Pro unlock) · a subscription, credits, or usage fees - Where does it run? approach
Mac only · Windows only or Linux only · several desktop systems · phone only · desktop and phone - Does it also record meetings or calls? approach
yes · no - Is 'your voice never leaves your device' the headline promise? value
yes, it is the main promise · one of several selling points · no, not a focus
Sources
Show HN posts 2026-07-27 to 2026-10-25 in this kind, plus well-known reference projects.
42 sources across 22 projects, read on 2026-10-26. Each project page lists its own. Poll version: core-v4.