FreeFlow

Productivity

voice dictation

SHOW HN2026

Legend

FreeFlow

Free alternative to Wispr Flow, Superwhisper, and Monologue

github.com

#speech to text#dictation#push to talk#whisper#macos

277points
132comments
#167of 4,366 in 2026
Top 4%of 2026 by points

How HN took it

CuriousMostly questions and neutral comments

4 positive, 21 neutral or asking, 1 mixed, 7 critical, out of 33 comments about the project. Thread score -0.12.

Idea: 1 for, 3 againstExecution: 0 for, 2 againstDesign: 2 for, 0 againstPerformance: 1 for, 0 againstPrivacy: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Local dictation tools like Handy and Parakeet models work well

    From 3 comments
    • Was searching for this this morning and settled on https://handy.computer/
      digitalbase on HN
    • Yes, I also use Handy. It supports local transcription via Nvidia Parakeet TDT2, which is extremely fast and accurate. I also use gemini 2.5 flash lite for post-processing via…
      hendersoon on HN
    • Big fan of handy and it’s cross platform as well. Parakeet V3 gives the best experience with very fast and accurate-enough transcriptions when talking to AIs that can read…
      d4rkp4ttern on HN

Objections

  • Groq dependency and post-processing latency; local LLM pipeline is too slow

    From 2 comments
    • I love this idea, and originally planned to build it using local models, but to have post-processing (that's where you get correctly spelled names when replying to emails / etc),…
      zachlatta on HN
    • I just learned about Handy in this thread and it looks great! I think the biggest difference between FreeFlow and Handy is that FreeFlow implements what Monologue calls "deep…
      zachlatta on HN
  • Free tier may disappear, a rug-pull risk

    From 2 comments
    • I built something similar for Linux (yapyap — push-to-talk with whisper.cpp). The "local is too slow" argument doesn't hold up anymore if you have any GPU at all. whisper…
      lxe on HN
    • Saved you a click: actually Grok, local inference too slow. Won't be free when xAI starts charging.
      Zopieux on HN
  • Screenshot approach is overkill for name spelling; accessibility APIs suffice

    From 2 comments
    • I built something similar for Linux (yapyap — push-to-talk with whisper.cpp). The "local is too slow" argument doesn't hold up anymore if you have any GPU at all. whisper…
      lxe on HN
    • The latency bottleneck with local post-processing is interesting. Sending a screenshot to a vision LLM is expensive, but you don't actually need full image understanding for most…
      anvevoice on HN

Requests

  • Support local models such as Parakeet

    From 1 comment
    • Could you make it use Parakeet? That's an offline model that runs very quickly even without a GPU, so you could get much lower latency than using an API.
      arcologies1985 on HN
  • Customisable key bindings and toggle mode

    From 1 comment
    • Is it possible to customise the key binding? Most of these services let you customise the binding, and also support toggle for push-to-talk mode.
      lemming on HN
  • Android, iOS and Windows versions

    From 3 comments
    • Does anyone know of an effective alternative for Android?
      spelk on HN
    • Anything similar for iOS?
      DevX101 on HN
    • Do any of these works as an iOS keyboard to replace the awful voice transcription Apple is currently shipping?
      johnbatch on HN

Questions

  • Does it work reliably for non-English languages such as Swedish?

    From 1 comment
    • Does any of these solutions work reliably for non-English languages? I’ve had a lot of issues trying to transcribe Swedish with all the products I’ve used so far.
      strokirk on HN
  • Which key combinations are used to record

    From 1 comment
    • For those using something like this daily, what key combinations do you use to record and cancel. I’m using my capslock right now but was curious about others
      muratsu on HN

Alternatives named

  • Handy

    From 2 comments
    • Was searching for this this morning and settled on https://handy.computer/
      digitalbase on HN
    • I just learned about Handy in this thread and it looks great! I think the biggest difference between FreeFlow and Handy is that FreeFlow implements what Monologue calls "deep…
      zachlatta on HN
  • Hex

    From 1 comment
    • Big fan of handy and it’s cross platform as well. Parakeet V3 gives the best experience with very fast and accurate-enough transcriptions when talking to AIs that can read…
      d4rkp4ttern on HN
  • MacWhisper

    From 1 comment
    • Since many are asking about apps with simillar capabilities I’m very happy with MacWhisper. Has Parakeet, near instant transcription of my lengthy monologues. All local.
      vesterde on HN
  • VoiceInk

    From 1 comment
    • There's also an offline-running software called VoiceInk for macos. No need for groq or external AI. https://github.com/Beingpax/VoiceInk
      p0w3n3d on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/47040375)