43 points | by Leftium 4 hours ago ago
17 comments
Why does the title specify the language used when it's not even mentioned on the home page?
this is a great landing page. I downloaded.
great onboarding too, using it now.
Very handy, thanks!
Read the creator's description in the original Show HN: https://hw.leftium.com/#/item/44302416
How good will this local model be compared to, say, your iphone builtin STT?
Very cool. Uses whiper small uder the hood.
https://github.com/openai/whisper
nvidia parakeet v3 was the default out of the box and it works surprisingly well
it offers all the different sizes of openai models too
TypeScript 53.9% Rust 44.9%
FYI
The README is very clear about it:
Frontend: React + TypeScript with Tailwind CSS for the settings UI Backend: Rust for system integration, audio processing, and ML inference
Lmao. At least it's typescript and not JavaScript!
Who’s gonna tell him?
Don’t you dare!
That's great, nice to see more and more projects of Machine learning being written in rust
Anyone know of the opposite? A really easy-to-use text-to-speech program that is cross-platform?
I've tried a lot of them, and the best I found so far is Edge browsers built in microsoft (natural) voices, which I call via javascript or the browsers read aloud function.
Checkout https://github.com/rany2/edge-tts , which exposes it as a Python library and a CLI tool.
I've used Speech Note, which works well for STT and TTS.
It downloads the model at first execution and also checks versions in github.
That is ok for what is brings. Nice program. Very "handy".
Why does the title specify the language used when it's not even mentioned on the home page?
this is a great landing page. I downloaded.
great onboarding too, using it now.
Very handy, thanks!
Read the creator's description in the original Show HN: https://hw.leftium.com/#/item/44302416
How good will this local model be compared to, say, your iphone builtin STT?
Very cool. Uses whiper small uder the hood.
https://github.com/openai/whisper
nvidia parakeet v3 was the default out of the box and it works surprisingly well
it offers all the different sizes of openai models too
TypeScript 53.9% Rust 44.9%
FYI
The README is very clear about it:
Frontend: React + TypeScript with Tailwind CSS for the settings UI Backend: Rust for system integration, audio processing, and ML inference
Lmao. At least it's typescript and not JavaScript!
Who’s gonna tell him?
Don’t you dare!
That's great, nice to see more and more projects of Machine learning being written in rust
Anyone know of the opposite? A really easy-to-use text-to-speech program that is cross-platform?
I've tried a lot of them, and the best I found so far is Edge browsers built in microsoft (natural) voices, which I call via javascript or the browsers read aloud function.
Checkout https://github.com/rany2/edge-tts , which exposes it as a Python library and a CLI tool.
I've used Speech Note, which works well for STT and TTS.
It downloads the model at first execution and also checks versions in github.
That is ok for what is brings. Nice program. Very "handy".