From add870e183125b4ee6a5bac5e2d5b0591342dbd7 Mon Sep 17 00:00:00 2001 From: leonardotrapani Date: Mon, 2 Feb 2026 11:32:38 +0100 Subject: [PATCH] feat: update readme --- README.md | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 1c4633d..0b40c16 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # Hyprvoice - Voice-Powered Typing for Wayland/Hyprland -26 voice models, cloud and local, built for Wayland dictation. +26 voice models, cloud and local, built for hyprland dictation. Press a toggle key, speak, and get instant text input. Built natively for Wayland/Hyprland with clean PipeWire capture and robust text injection. @@ -8,11 +8,12 @@ Press a toggle key, speak, and get instant text input. Built natively for Waylan - 26 speech-to-text models across cloud and local providers, including whisper.cpp. - Streaming and batch transcription with 57-language support and model-language validation. -- Optional LLM post-processing plus keywords to preserve names and technical terms. +- Optional LLM post-processing for grammar, punctuation, and more. - Toggle workflow with optional status notifications and cancel support. - Text injection via ydotool, wtype, and clipboard fallback with clipboard restore. - Guided onboarding and a full configure menu with hot-reload. - Personalization through custom prompt and keywords sent both to LLM and to voice model. +- Whisprflow quality but for linux and open source. ## Voice Providers and Models @@ -51,8 +52,6 @@ All supported speech-to-text providers and models: - `nova-3` - `nova-2` -Language coverage: 57 languages overall; Deepgram models cover a subset; English-only models are labeled above. - ## Installation (AUR) ```bash