AI Rank
EN
← 开源
goodroot

hyprwhspr

Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation

ApplicationsPersonalPython
在 GitHub 打开
增长势头
+124 小时新增 Star+0.1%
1.24k
Star
104
Fork
+8
本周
56
贡献者
创建于 2025-08-27 · 更新于 2026-10-16 · 今日第 5705 名
主要开发者
goodrootsqondeNasicus

goodroot/hyprwhspr 排名第 5,705，有 1,242 个星标。

同类别比较

goodroot/hyprwhspr 排名第 5,705，此处有 8 个同类条目；thClaws/thClaws 排名第 5,708。

同类别比较
名称排名指标
JayWebtech/autoshorts5,689
语言:
Rust
星标数:
1,256
分叉数:
237
简介:
AutoShorts is a local-first desktop application for turning long-form video or audio recordings into high-impact, vertical short-form clip candidates (9:16 portrait) with AI-powered viral moment ranking.
NeymarL/ChineseChess-AlphaZero5,694
语言:
Python
星标数:
1,250
分叉数:
361
简介:
Implement AlphaZero/AlphaGo Zero methods on Chinese chess.
RhythmicWave/NovelForge5,695
语言:
Python
星标数:
1,248
分叉数:
226
简介:
AI辅助长篇小说创作，卡片式创作，支持基于 JSON Schema的结构化 AI 生成与上下文引用，可扩展性强。
bowang-lab/MedRAX5,699
语言:
Python
星标数:
1,246
分叉数:
207
简介:
MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025
thClaws/thClaws5,708
语言:
Rust
星标数:
1,238
分叉数:
183
taranis-ai/taranis-ai5,717
语言:
Python
星标数:
1,229
分叉数:
181
简介:
Taranis AI is an advanced Open-Source Intelligence (OSINT) tool, leveraging Artificial Intelligence to revolutionize information gathering and situational analysis.
aydinnyunus/ai-captcha-bypass5,722
语言:
Python
星标数:
1,225
分叉数:
132
简介:
AI Captcha Bypass
SalesforceAIResearch/enterprise-deep-research5,733
语言:
Python
星标数:
1,217
分叉数:
190
简介:
Salesforce Enterprise Deep Research
关键参数与规格
关键参数与规格
参数值
语言Python
类别Applications
子类别Personal
关键词LocalAI, Speech-to-text
星标数1,242
分叉数104
贡献者56
创建日期2025-08-27
更新日期2026-10-16
1 天星标数1
7 天星标数8
排名5,705
上次排名5,859
排名变化154
7 天星标排名4,505
上次 7 天星标排名4,779
7 天星标排名变化274
总星标排名9,429
上次总星标排名9,425
总星标排名变化-4
国家Canada
README 摘录

Latest and greatest **GPU memory efficient** - Limit or zero memory usage easily, more for other local models **onnx-asr for wild CPU speeds** - No GPU? Optimized for great speed on any hardware **Strong CJK** - Qwen3-ASR for Chinese, Japanese and Korean **Translation** - Translate non-English to English with a single config **REST API or websockets** - Secure, fast wires to top clouds like Gemini, ElevenLabs **Live streaming** - Self-host NeMo or Phonon: watch words form, or type as you speak (experimental

) **Themed visualizer** - Visualizes your voice, will automatch Omarchy and Noctalia themes **Word overrides and prompts** - Custom hot keys, common words, and more **Multi-lingual** - Great performance in many languages **Long form mode with saving** - Pause, think, resume, pause: submit. This one is built ground-up for performance and stability: your hardware will auto-optimize to the **best possible accuracy and speed**. Actively maintained, at the leading edge, fully featured, strictly offline unless you use an API, and works on both

Wayland and X11. 14** **Wayland or X11 session** (GNOME, KDE Plasma, Sway, Hyprland, Niri, etc. Manual install Nix and NixOS (beta) Use the Nix flake and NixOS module for x86_64 Linux with Whisper. We'd appreciate issue reports and requests! ✅ Configure transcription backend (Cohere Transcribe, Parakeet TDT V3, Whisper, Qwen3-ASR, REST API, or Realtime WebSocket) 2. ✅ Configure themed visualizer for maximum coolness (optional) 4. ✅ Validate installation First use Ensure your microphone of choice is available in audio settings! **Log

out and back in** (for group permissions) 2. **Press ** again to stop dictation - _boop! Updating Managed release rollout and recovery: installation guide. CLI commands - Interactive initial setup - Update a managed release - Inspect managed installation state - Repair a managed installation - Manage configuration ( / / / ) - Manage models ( / / / / ) - External hotkey control ( / / / / / / / / ) - Transcribe a WAV or MP3 file to stdout (use to write a file) - Overall status check - Validate installation - Test microphone and transcription end-to-end - List/test keyboard devices ( / ) / - Manage bar integration - Enable/disable

the mic OSD ( / / ) - Manage systemd services - Remove hyprwhspr; preserve settings, credentials and models - Also remove recorded personal files ( preserves models) Documentation All of it at **hyprwhspr. Contributing Start with an issue - happy to help! Upvotes on the AUR and/or GitHub stars are also a nice way to show appreciation.

常见问题

记录了多少星标和分叉？

goodroot/hyprwhspr 有 1,242 个星标和 104 个分叉。

仓库排名是多少？

goodroot/hyprwhspr 排名第 5,705。

记录的语言和类别是什么？

goodroot/hyprwhspr 有 1,242 个星标，语言为 Python，类别为 Applications。

哪个仓库排名最接近？

goodroot/hyprwhspr 与 thClaws/thClaws 比较，后者排名第 5,708，有 1,238 个星标。

README
hyprwhspr





Native speech-to-text for Linux - Fast, accurate, private and hackable system-wide dictation





instant performance | Cohere / Parakeet / Whisper / Qwen3-ASR / ElevenLabs / REST API | stylish visuals





Supports Arch, Debian, Ubuntu, Fedora, openSUSE and more





 [hyprwhspr.com](https://hyprwhspr.com)

https://github.com/user-attachments/assets/4c223e85-2916-494f-b7b1-766ce1bdc991

  • Built for Linux - Native AUR package for Arch, or use Debian/Ubuntu/Fedora/openSUSE/NixOS
  • Very fast defaults - Nearly instant and accurate performance via in-memory models
  • Offline and private - Transcription never leaves your machine. Cloud APIs are fully optional.
  • Latest models - Cohere Transcribe? Orukeet? Parakeet TDT V3? Qwen3-ASR? Latest and greatest
  • GPU memory efficient - Limit or zero memory usage easily, more for other local models
  • onnx-asr for wild CPU speeds - No GPU? Optimized for great speed on any hardware
  • Strong CJK - Qwen3-ASR for Chinese, Japanese and Korean
  • Translation - Translate non-English to English with a single config
  • REST API or websockets - Secure, fast wires to top clouds like Gemini, ElevenLabs
  • Live streaming - Self-host NeMo or Phonon: watch words form, or type as you speak (experimental)
  • Themed visualizer - Visualizes your voice, will automatch Omarchy and Noctalia themes
  • Word overrides and prompts - Custom hot keys, common words, and more
  • Multi-lingual - Great performance in many languages
  • Long form mode with saving - Pause, think, resume, pause: submit... Bam!
  • Auto-paste anywhere - Instant paste into any active buffer, or even auto enter (optional)
  • Audio ducking 🦆 - Reduces or pauses other audio on record (optional)

Why hyprwhspr? There are a lotta dictation apps. This one is built ground-up for performance and stability: your hardware will auto-optimize to the best possible accuracy and speed. Actively maintained, at the leading edge, fully featured, strictly offline unless you use an API, and works on both Wayland and X11.

Quick start

Prerequisites

  • Linux with systemd (Arch, Debian, Ubuntu, Fedora, openSUSE, NixOS etc.)
  • Python 3.11-3.14
  • Wayland or X11 session (GNOME, KDE Plasma, Sway, Hyprland, Niri, etc.).
  • Clipboard/window tools:
    • wl-clipboard and wtype on Wayland
    • python-pyperclip, xclip, xdotool, and xprop on X11 (installed by the dependency script)
  • Waybar or Noctalia (optional, for status bar)
  • gtk4 + PyCairo (optional, for visualizer)
  • NVIDIA GPU (optional, for CUDA acceleration)
  • AMD/Intel GPU / APU (optional, for Vulkan acceleration)

Install

Arch Linux

On the AUR:

# Install for stable
yay -S hyprwhspr

# Or install for bleeding edge
yay -S hyprwhspr-git

Then run the interactive setup:

hyprwhspr setup

Ubuntu, Debian, Fedora, openSUSE

curl -fsSL https://hyprwhspr.com/install.sh | bash

Installs dependencies, clones to ~/.local/share/hyprwhspr/src, and walks you through setup.

Manual install

# Clone the repo
git clone https://github.com/goodroot/hyprwhspr.git
cd hyprwhspr

# Install dependencies for your distro
./scripts/install-deps.sh

# Run interactive setup
./bin/hyprwhspr setup

Nix and NixOS (beta)

Use the Nix flake and NixOS module for x86_64 Linux with Whisper.cpp CPU transcription.

We'd appreciate issue reports and requests!

Setup then walks you through:

  1. ✅ Configure transcription backend (Cohere Transcribe, Parakeet TDT V3, Whisper, Qwen3-ASR, REST API, or Realtime WebSocket)
  2. ✅ Download models
  3. ✅ Configure themed visualizer for maximum coolness (optional)
  4. ✅ Configure bar integration for your shell -- Waybar or Noctalia (optional)
  5. ✅ Set up systemd user services
  6. ✅ Set up permissions
  7. ✅ Validate installation

First use

Ensure your microphone of choice is available in audio settings!

  1. Log out and back in (for group permissions)
  2. Press Super+Alt+D to start dictation - beep!
  3. Speak naturally
  4. Press Super+Alt+D again to stop dictation - boop!
  5. Bam! Text appears in active buffer!

What you'll see while recording: on layer-shell compositors (Hyprland, Sway, niri, KDE) the animated mic OSD overlay -- on Noctalia / Omarchy it auto-matches your live shell theme; on GNOME/Mutter you may need to make additional changes. See Themed visualizer for details.

Any snags, please create an issue.

Updating

# Arch: update via your AUR helper
yay -Syu hyprwhspr

# Managed release installs
hyprwhspr update

# Legacy bootstrap installs: re-run the installer
curl -fsSL https://hyprwhspr.com/install.sh | bash

# Either way, setup is idempotent if you need to re-run it
hyprwhspr setup

Managed release rollout and recovery: installation guide.

CLI commands

  • hyprwhspr setup - Interactive initial setup
  • hyprwhspr update [--version VERSION] - Update a managed release
  • hyprwhspr install status - Inspect managed installation state
  • hyprwhspr install repair [--python PATH] - Repair a managed installation
  • hyprwhspr config - Manage configuration (show / show --all / edit / secondary-shortcut)
  • hyprwhspr model - Manage models (download / list / status / unload / reload)
  • hyprwhspr record - External hotkey control (start / stop / toggle / cancel / capture / status / copy-last / paste-last / clear-last)
  • hyprwhspr transcribe INPUT - Transcribe a WAV or MP3 file to stdout (use -o PATH to write a file)
  • hyprwhspr status - Overall status check
  • hyprwhspr validate - Validate installation
  • hyprwhspr test - Test microphone and transcription end-to-end
  • hyprwhspr keyboard - List/test keyboard devices (list / test)
  • hyprwhspr waybar / hyprwhspr noctalia - Manage bar integration
  • hyprwhspr mic-osd - Enable/disable the mic OSD (enable / disable / status)
  • hyprwhspr systemd - Manage systemd services
  • hyprwhspr uninstall - Remove hyprwhspr; preserve settings, credentials and models
  • hyprwhspr uninstall --purge - Also remove recorded personal files (--keep-models preserves models)

Documentation

All of it at hyprwhspr.com/docs, or here:

Getting help

License

MIT License - see LICENSE file.

Contributing

Start with an issue - happy to help! Pull requests best begin there too.

Upvotes on the AUR and/or GitHub stars are also a nice way to show appreciation.

Built with ❤️ in 🇨🇦

排名相邻
同类项目