Freestyle Voice

Open source voice dictation app turning your voice into clean text. Stop typing, speak freely.

[Freestyle Voice @FreestyleVoice]

The current status of Freestyle...

"Is PostHog down" ➡️ "Is post-hug down."

1.12s inference

Yeah we have a long way to go 😂

[Freestyle Voice @FreestyleVoice]

It's local. We do not have a cloud ourselves. On Freestyle, you can select a local model that runs on device, like whisper.cpp, and Qwen. This ensures your voice and recording never leave your device.

We also do provide the option to use cloud transcription models. Bring your own API key. If you use gpt-4o-transcribe, for example, your recording will go to OpenAI's cloud for transcription.

Hope that makes sense!

[Freestyle Voice @FreestyleVoice]

Excited to announce that we're launching Freestyle!

Freestyle is the dictation app that converts your voice into text. Hold down a hotkey, talk, and clean text will appear wherever your cursor is. Speak 4X faster than you type.

Freestyle is free, open source, and local first, ensuring your dictations are private and never leaves your device.

A couple of highlight features:

1️⃣ Transcription post-processing: grammer and punctuation cleanup via post-processing. No more "um, oh, but".

2️⃣ Choose your own models, cloud or local on-device

3️⃣ Dictionary: custom phrase replacements applied after transcription. (ex. "type script" → TypeScript).

Try it out today!

https://t.co/aU2w5Zy2Np

[Freestyle Voice @FreestyleVoice]

@JeremyKrak @rileybrown How's the latency and accuracy compared to Wispr?

[Freestyle Voice @FreestyleVoice]

@robert__blaga @rileybrown We're free, also open source 👀

[Freestyle Voice @FreestyleVoice]

Hey Avi, I'm Matt, I maintain the Freestyle project, we're also building an oss dictation app.

Really cool project! Saw the demo and was really impressed with the latency. I find getting sub-second latency with high accuracy and post-processing be one of the biggest challenges to building good dictation.

We're trying to build an oss dictation app that feels just as optimized as Wispr.

I'd love to have you check out our project, we've got a pretty active community on Discord with ppl trying to solve these exact problems.

You seem talented, would love to have you help out.

[Freestyle Voice @FreestyleVoice]

Hey Riley, I'm Matt and I maintain the Freestyle project.

I was a huge Wispr user, but I find their subscription model and valuation to be insane. That's been my motivation to build a free, oss alternative that feels just as optimized.

To get Freestyle to feel just as good, there's a ton of interesting work around post-processing and optimizing for sub-minute transcription latency. Trying to grow our community and catch up to Wispr.

We actually just launched it today. Hope you get to check it out!

https://t.co/khlDPtEdET

[Freestyle Voice @FreestyleVoice]

@geekbb Thank you so much for sharing our project!!

[Freestyle Voice @FreestyleVoice]

@shikhr_ Thanks for working so hard on it!

[Freestyle Voice @FreestyleVoice]

Lately, speech-to-text voice dictation apps like
@WisprFlow have taken the world by storm. Credit where it's due, it's a genuinely polished product. Low latency, the post-processing is great, the product feels premium. It’s changed how we do work.

But a couple things didn't sit right with me. You're paying $12 a month for it. Every sound you make, every word you say and every transcription passes through their servers. It’s a standing risk to your privacy.

There's no reason your private thoughts ever have to leave your device. Plenty of open-source dictation tools already exist, but none of them feel as polished as the paid apps, and that gap is what we want to close.

Voice dictation is a commodity and should be free and open source.

It's an early preview with lots to build, so we'd genuinely love contributors. Freestyle is a technically challenging and ridiculously fun project to work on. We’re looking to grow our community.

If this sounds interesting, come build with us!

https://t.co/khlDPtEdET

[Freestyle Voice @FreestyleVoice]

@souvenger @ParthJadhav8 Hey Sourav, I'm Matt, I maintain Freestyle voice project. would love to have you join our community and contribute!

We've got a pretty active group, and lots of discussions going on.

[Freestyle Voice @FreestyleVoice]

@NonDualistCoder @shikhr_ @ParthJadhav8 Really appreciate the shoutouts @NonDualistCoder @shikhr_ !

[Freestyle Voice @FreestyleVoice]

@ParthJadhav8 Hey Parth, I'm Matt, I'm the maintainer of Freestyle. We're building an open source voice dictation app!

The project is a little over a week old. We have a small community of devs working on it. Would love to have you check it out, join our community working on it!