Ben Lang

OpenWispr - 100% local open source AI speech-to-text model

Turn your voice into formatted text. It's open source and runs 100% locally. 3-5x faster than typing, and especially helpful when prompting LLMs, writing emails and sending texts. Pick your preferred model, and even edit the system prompt. Take full control.

Add a comment

Replies

Best
Gabe Stein
Maker
📌

I honestly couldn’t justify paying for another ai tool subscription, so I built this one myself.

OpenWispr, is an open source speech-to-text tool that runs 100% locally and helps you write 3-5x faster than typing.

It's especially helpful for prompting in ChatGPT, Claude and/or Cursor but really I use it for everything. I have found that LLMs are able to match your tone more closely when you speak to them, rather than when you type (as it forces you to articulate yourself more and you edit out your natural tone).

It's completely free if you clone the repo and run it yourself, otherwise for a small contribution you get access to automatic updates as they roll out.

Try it out and let me know what you think! DM me if you need help setting it up :)

Masum Parvej

@gabe_stein Would love to see this integrated into IDEs like VS Code

Gabe Stein

@masump it already works with VS code! Can you expand what you mean by integrated? :)

Benhur Senabathi

Very excited to use this, love open source projects!

Gabe Stein

@benhur_senabathi Appreciate it! Please let me know if you need any help getting set up!

Kartike Bansal

@gabe_stein Congrats on the launch! A local, open source voice-to-text tool sounds incredibly useful for faster prompting and writing.

Gabe Stein

@kraten Appreciate it! Give it a try and let me know what you think :)

Quico Benford

nice workk, team. What languages/accents does it handle well right now, and is there real‑time streaming for live captions? Also, is there a quickstart (Docker or one‑click) so I can go from install → first transcript in under 10 minutes?

Gabe Stein

@quico_benford we supported 49 languages! You can see the full list here: https://github.com/HeroTools/open-wispr/blob/main/src/utils/languages.ts . No real time streaming yet! And yes you could definitely clone the repository and get it running in less than 10 mins! There is a full breakdown of how to get set up on our github :)

Joey Judd

Wow, running everything locally without sending my voice data anywhere? That’s huge—I’m always sketchy about cloud stuff. Love that you let us edit the system prompt too!

Gabe Stein

@joey_zhu_seopage_ai appreciate it! Let me know if you neee any help setting it up :)

Gabe Perez

This is super awesome. I actually really wanted a local version of @Aqua Voice and this might be the answer. @gabe_stein awesome job. How does it compare in terms of speed & accuracy agains @Wispr Flow or @Aqua Voice ?

Getting it as I type!

Gabe Stein

@gabe I’d say pretty much the same! Especially if you use the cloud processing :) we’re all using the same models in the background!

Rohan Gayen

Was looking for this for long time. Thank you.

Can you add model API providers with free limits eg. Groq and Gemini?

Gabe Stein

you can bring your own API key! Will add Groq and Gemini as options soon :) right now it is OpenAI and Anthropic.

Rohan Gayen

@gabe_stein Thanks. Also would love to see exe file along with the mac installers.

Alexandru Rada

what languages are supported?

Gabe Stein

@alxrda we supported 49 languages! You can see the full list here: https://github.com/HeroTools/open-wispr/blob/main/src/utils/languages.ts

Alexandru Rada

@gabe_stein nice. Looking to get this integrated into the AI Assistant I'm building.
Congrats!!!

You deserve a follow!

Sig Eternal

Another awesome open-source product! How many language does it currently detect?

Gabe Stein

@sig_eternal we support 49 languages! You can see the full list here: https://github.com/HeroTools/open-wispr/blob/main/src/utils/languages.ts :)

Vividkreations

OpenWispr empowers seamless and secure voice communication through AI-driven whisper technology. Experience crystal-clear, low-latency audio solutions built for privacy, clarity, and real-time collaboration across platforms and devices.

Kevin Coffey

Is this available for Windows or just Mac?

Gabe Stein

@kevin_coffey Hey Kevin - should work on Windows :) I've sent you and email if you'd like to discuss further!