HNHacker News
TopNewBestAskShowJobs

braden-w

223 karma · joined April 5, 2022

submissionscomments
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Thank you! And you’re right, I think Whisper struggles with younger voices. Haven’t tested Parakeet or other models for this yet, but that’s a great use case (especially since privacy matters in education). I would also shoutout Hypernote! (https://hyprnote.com/) They might be expanding their model options, as they have shown with OWhisper (https://docs.hyprnote.com/owhisper/what-is-this).
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Not yet, but I want it too! Parakeet looks incredible (saw that leaderboard result). My current roadmap is: finish stabilizing whisper.cpp integration, then add Parakeet support. If anyone has bandwidth to PR the connector, I’d be thrilled to merge it.
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Great catch Aachen, I should have clarified this better. The app supports both external APIs (Groq, OpenAI, etc.), and more recently local transcription (via whisper.cpp, OWhisper, Speaches, etc.), which never leaves your device.

Like Leftium said, the local-first Whisper C++ implementation just posted a few hours ago.

braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Yes, we currently support OpenAI/ElevenLabs/Deepgram APIs that all use non-Whisper models (presumedly) under the hood. Speaches also supports other models that are not Whisper. Hopefully adding Parakeet support later too!
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Ahh that's unfortunate. This most likely is related to the rust `enigo` create, which we use to write text to the cursor. You can see the lines in question here: https://github.com/epicenter-so/epicenter/blob/60f172d193d88...

If it's still an issue, feel free to build it locally on your machine to ensure your supply chain is clean! I'll add more instructions in the README in the future.

braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
LOL that's pretty funny, thank you for the share!
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Commented this earlier, but I'm in the middle of a release that adds Whisper C++ support! https://github.com/epicenter-so/epicenter/pull/655

After this pushes, we'll have far more extensive local transcription support. Just fixing a few more small things :)

braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Amazing, thanks for giving it a try! Let me know how it goes and feel free to message me any time :) happy to add any features that you miss from closed-source altneratives!
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Hmm, we support prompts at both 1. the model level (the Whisper supports a "prompt" parameter that sometimes works) and 2. transformations level (inject the transcribed text into a prompt and get the output from an LLM model of your choice). Unsure how else semantic correction can be implemented, but always open expand the feature set greatly over the next few weeks!
braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
For those checking out the repo this morning, I'm in the middle of a release that adds Whisper C++ support!

https://github.com/epicenter-so/epicenter/pull/655

After this pushes, we'll have far more extensive local transcription support. Just fixing a few more small things :)

braden-w··on Show HN: Whispering – Open-source, local-first dictation you can trust
Thank you for checking it out! Coincidentally, it's on the way:

https://github.com/epicenter-so/epicenter/pull/661

In the middle of a huge release that sets up FFMPEG integration (OWhisper needs very specifically formatted files), but hoping to add this after!

braden-w··on Show HN: Whispering – An open-source alternative to Superwhisper
Hey HN,

I couldn’t find an open-source alternative to Superwhisper, Wispr Flow, etc. that I liked, so I built my own.

It’s free, cross-platform, runs locally or in the cloud with your own API key, and works via system-wide hotkey or voice-activated detection.

Under the hood, it’s built with Svelte 5 + Rust/Tauri, which makes it extremely lightweight (~22 MB on macOS) and performant.

GitHub → https://github.com/you/whispering

Releases → https://github.com/you/whispering/releases

Live demo/web → https://whispering.bradenwong.com

I’ve been using it daily for months and just shipped v7—would love your feedback!

braden-w··on Show HN: Open-source transcription that costs $0.02/hour instead of $30/month
For those interested in the architecture: I use dependency injection at build time to share ~95% of code between desktop and web versions. Instead of maintaining separate codebases, I detect the platform and inject the appropriate service implementations.

The three-layer architecture has been particularly helpful:

- Services: https://github.com/braden-w/whispering/tree/main/apps/app/sr...: Pure functions with platform abstraction, no UI dependencies

- Query layer: https://github.com/braden-w/whispering/tree/main/apps/app/sr... : Adds reactivity, caching, and runtime dependency injection

Voice-activated mode is particularly nice when coding—you can keep your hands on the keyboard while dictating. The Svelte 5 runes + TanStack Query combination has been fantastic for managing real-time audio state.

← PreviousPage 2 of 2