Free to start · Open source

Free Dictation Software for Every App You Use

Press a hotkey, speak, and clean, punctuated text appears anywhere — email, docs, Slack, your editor or an AI chat. Run it privately on your device, or switch on OpenWhispr Cloud for top accuracy on any machine. Either way, your audio is never stored.

Free to start on macOS, Windows & Linux · No card, no account

Without OpenWhispr~40 WPM
Slack — #product

Type a message…

With OpenWhispr~150 WPM
Slack — #product

Press your hotkey and speak…

Hold the hotkey, speak, release — text lands in the active app.

Dictate into every app you already use

ChatGPT
ChatGPT
Claude
Claude
Cursor
Cursor
Gmail
Gmail
Slack
Slack
Google Docs
Google Docs
Teams
Teams

Why people switch

Most dictation software makes you trade something away.

Speed for privacy, privacy for accuracy, or your whole workflow for one company’s cloud. OpenWhispr is built so you don’t have to choose.

Your ideas outrun your fingers.

You speak several times faster than you type. OpenWhispr turns speech into clean text at the speed you think, so email, prompts and drafts stop getting squeezed through a keyboard.

You can’t see what most voice tools do with your voice.

Most dictation software is closed and cloud-only. OpenWhispr is open source, and whether you run it locally or on OpenWhispr Cloud, your audio is transcribed and never stored, sold, or used for training — verifiable in the code.

Your setup shouldn’t be locked to one app or OS.

Closed tools trap your workflow in their cloud and their platform. OpenWhispr runs on Mac, Windows and Linux, works in every app, and lets you bring your own AI keys — your workflow stays yours.

Built-in dictation isn’t enough.

Apple Dictation and Windows Speech are inaccurate, online-dependent and locked to one OS. OpenWhispr runs Whisper-class voice recognition on all three platforms, with a custom dictionary for your names and jargon.

What you get

One hotkey between your voice and every app.

Dictation software that works wherever your cursor is — dictate emails, prompt AI, and capture ideas with no destination app to copy and paste from.

Dictate into any app

Press the hotkey, speak, release. Punctuated text appears wherever your cursor is — email, docs, Slack, your code editor. Nothing to copy and paste.

Talk to AI instead of typing at it

Speak long, context-rich prompts into ChatGPT, Claude or Cursor. Dictation is the fastest way to give AI the detail it needs for a better answer.

Accurate in your words

Teach OpenWhispr your names, jargon and acronyms with a custom dictionary, then pick the engine that fits — run locally, or switch on OpenWhispr Cloud for top accuracy on any machine.

Dictate in

100+

languages, with translation built in

Recordings stored

0

local audio never leaves your device; cloud audio is transcribed, then discarded

Setup takes

5 min

from download to your first dictated sentence

How it works

Talk to your computer in three steps.

No cloud account, no signup. Just software on your machine, running in about five minutes.

1

Download for free.

Mac, Windows or Linux. Pick a local model, or use OpenWhispr Cloud — no account, no card.

2

Set your hotkey.

One shortcut — hold-to-record or push-to-toggle — working system-wide across every app.

3

Press. Speak. Done.

Clean, punctuated text lands wherever your cursor is, in 100+ languages.

No convincing needed

10 reasons people make OpenWhispr their dictation software

Switching is a trust decision. Every claim here is verifiable in the open-source repo.

Works in every app

A system-wide hotkey. If you can place a cursor there, you can dictate there.

Private by design, and auditable

Open source with zero data retention — local audio stays on your device, and cloud audio is transcribed then discarded.

Local or cloud — your call

Run on-device for full privacy, or switch on OpenWhispr Cloud for top accuracy and speed on any machine.

Whisper-class and Parakeet accuracy

The leading open speech-to-text models, plus a cloud option that keeps up on modest hardware.

A custom dictionary for your words

Teach it names, jargon and acronyms so your transcripts come out right the first time.

100+ languages plus translation

Speak one language, output another — set a language or auto-detect on the fly.

Bring your own AI keys

Use your own OpenAI, Anthropic, Gemini or Groq keys for unlimited cloud transcription, no markup.

Clean up as you speak

A built-in AI writing assistant reformats and polishes raw dictation — locally or in the cloud.

Mac, Windows & Linux

One of the only dictation apps that runs natively on all three, with the same features everywhere.

Easier on your hands

If typing is slow, tiring or painful — RSI, fatigue, long days — your voice does the work instead.

Before you download

Common questions about OpenWhispr dictation software

What users say

People who stopped typing.

Gabe | ガブ
Gabe | ガブ
@gabe__perez

My favorite thing on @producthunt today is OpenWhispr. I love @aquavoice_ but really need a local model for when I'm traveling or don't have WiFi. This perfectly solves it. UI and Performance are great.

shai
shai
@shaiunterslak

OpenWhispr is goated

Keisuke
Keisuke
@_AlwaysAI

Translated from Japanese

The best voice input solution I've found recently. I was using Aqua Voice before, but this is OSS with the same features and feel — plus you can choose between API-based pay-as-you-go or downloading a local ASR model!

DJ
DJ
@DuaneJRich

Reading is faster than listening, and speaking is faster than writing. Makes me think the highest throughput person-to-AI mode will be voice to text and reading / evaluating outputs. I'm trying this with OpenWhispr for voice to text.

MV
MV
@MaximVovshin

OpenWhispr is a really good open source alternative for WisprFlow!

Adrian Nutiu
Adrian Nutiu
@AdrianNutiu

Whisper Base local is near instant in OpenWhispr, and I found it better than Parakeet. Parakeet is near instant, too.

Anagh
Anagh
@heyanaghh

I think it's changed the game when you can talk to it and then it can talk back. I'm using OpenWhispr (found on GitHub) with OpenAI Whisper Turbo and it works seamlessly.

0xSero
0xSero
@0xSero

Started using OpenWhispr with my local models & hardware, I have to say this is better than typing.

j3iiifn
j3iiifn
@j3iiifn

Translated from Japanese

I've gotten tired of the hassle of typing into Claude Code chats, so I tried using OpenWhispr for voice input instead. Even when I stumble and rephrase mid-sentence, the transcription comes out clean and polished, which makes me happy.

Pricing

Start free. Upgrade for cloud speed and more.

Unlimited local dictation is free forever. Pro and Business add unlimited OpenWhispr Cloud, meeting hours, mobile, and team features.

FreeFor everyone

$0

 

  • OpenWhispr Cloud
  • 2,000 words/week transcription
  • 5 hours of meeting recordings/month
  • Always free
  • Unlimited local AI models
  • Unlimited cloud transcription with your own API keys
  • 100+ languages supported
  • Custom dictionary
  • Zero data retention
  • Community support

ProFor individuals and teams

$6.67/user/mo

$80/user billed annually

All Free features +

  • Unlimited cloud transcription
  • 20 hours of meeting recordings/month
  • Sync across devices
  • Personal API access
  • MCP integration in all your apps
  • Mobile app (iOS Coming Soon)
  • Email support
Most Popular

BusinessFor individuals and teams

$16.67/user/mo

$200/user billed annually

All Pro features +

  • Unlimited meeting recordings
  • Speaker labels
  • Agent mode
  • Chat over your data
  • Priority support

EnterpriseFor advanced security & support

Custom

 

All Business features +

  • Team features & admin
  • SSO, SAML & SCIM
  • Audit logs & retention controls
  • Dedicated support

Built in the open

Your voice, handled the way you would handle it.

OpenWhispr started with a simple objection: most dictation software listens to everything you say from behind closed source. So we built ours in the open — every release and every line of code is on GitHub, where 3,100+ engineers have starred, forked and audited the project. Local or cloud, we never store, sell, or train on your data, and you can prove it by reading the code.

Your next sentence doesn’t need a keyboard.

Download OpenWhispr and dictate into any app on your computer — in 100+ languages, private by design, five minutes from now.

Free to start on Mac, Windows & Linux · No card, no account