# 🎙ī¸ W H I S P E R   V O I C E ### SOVEREIGN SPEECH RECOGNITION
![Status](https://img.shields.io/badge/STATUS-OPERATIONAL-success?style=for-the-badge&logo=server) [![Download](https://img.shields.io/gitea/v/release/lashman/whisper_voice?gitea_url=https%3A%2F%2Fgit.lashman.live&label=Download&style=for-the-badge&logo=windows&logoColor=white&color=2563eb)](https://git.lashman.live/lashman/whisper_voice/releases/latest) [![License](https://img.shields.io/badge/LICENSE-CC0_PUBLIC_DOMAIN-lightgrey?style=for-the-badge&logo=creative-commons&logoColor=black)](https://creativecommons.org/publicdomain/zero/1.0/)
> *"The master's tools will never dismantle the master's house."* — Audre Lorde >
> **Build your own tools. Run them locally.** [Report Issue](https://git.lashman.live/lashman/whisper_voice/issues) â€ĸ [View Source](https://git.lashman.live/lashman/whisper_voice) â€ĸ [Releases](https://git.lashman.live/lashman/whisper_voice/releases)

## ✊ The Manifesto **We hold these truths to be self-evident:** That user data is an extension of the self, and its exploitation by centralized clouds is a violation of digital autonomy. **Whisper Voice** is built on the principle of **technological sovereignty**. It provides state-of-the-art speech recognition without renting your cognitive output to corporate oligarchies. By running entirely on your own hardware, it reclaims the means of digital production, ensuring that your words remain exclusively yours. --- ## ⚡ Technical Architecture This operates on the metal. It is not a wrapper. It is an engine. | Component | Technology | Benefit | | :--- | :--- | :--- | | **Inference Core** | **Faster-Whisper** | Hyper-optimized implementation of OpenAI's Whisper using **CTranslate2**. Delivers **4x speedups** over PyTorch. | | **Quantization** | **INT8** | 8-bit quantization enables Pro-grade models (`Large-v3`) to run on consumer GPUs with minimal VRAM. | | **Sensory Gate** | **Silero VAD** | Enterprise-grade Voice Activity Detection filters out silence and background noise, conserving compute. | | **Interface** | **Qt 6 / QML** | Hardware-accelerated, glassmorphic UI that feels native yet remains OS-independent. | --- ## 📊 Intelligence Matrix Select the model that aligns with your hardware capabilities. | Model | VRAM (GPU) | RAM (CPU) | Velocity | Designation | | :--- | :--- | :--- | :--- | :--- | | `Tiny` | **~500 MB** | ~1 GB | ⚡ **Supersonic** | Command & Control, older hardware. | | `Base` | **~600 MB** | ~1 GB | 🚀 **Very Fast** | Daily driver for low-power laptops. | | `Small` | **~1 GB** | ~2 GB | ⏊ **Fast** | High accuracy English dictation. | | `Medium` | **~2 GB** | ~4 GB | ⚖ī¸ **Balanced** | Complex vocabulary, foreign accents. | | `Large-v3 Turbo` | **~4 GB** | ~6 GB | ✨ **Optimal** | **Sweet Spot.** Near-Large smarts, Medium speed. | | `Large-v3` | **~5 GB** | ~8 GB | 🧠 **Maximum** | Professional transcription. Uncompromised. | > *Note: Acceleration requires you to manually select your Compute Device (CUDA GPU or CPU) in Settings.* --- ## 🛠ī¸ Operations ### đŸ“Ĩ Deployment 1. **Download**: Grab `WhisperVoice.exe` from [Releases](https://git.lashman.live/lashman/whisper_voice/releases). 2. **Deploy**: Place it anywhere. It is portable. 3. **Bootstrap**: Run it. The agent will self-provision an isolated Python environment (~2GB) on first launch. ### 🕹ī¸ Controls * **Global Hook**: `F9` (Default). Press to open the channel. Release to inject text. * **Tray Agent**: Retracts to the system tray. Right-click for **Settings** or **File Transcription**. ### 📡 Input Modes | Mode | Description | Speed | | :--- | :--- | :--- | | **Clipboard Paste** | Standard text injection via OS clipboard. | Instant | | **Simulate Typing** | Mimics physical keystrokes. Bypasses anti-paste blocks. | Up to **6000** CPM | --- ## 🌐 Universal Translation The model listens in **99 languages** and translates them to English or transcribes them natively.
Click to view supported languages
| | | | | | :--- | :--- | :--- | :--- | | Afrikaans đŸ‡ŋđŸ‡Ļ | Albanian đŸ‡Ļ🇱 | Amharic đŸ‡Ē🇹 | Arabic 🇸đŸ‡Ļ | | Armenian đŸ‡Ļ🇲 | Assamese 🇮đŸ‡ŗ | Azerbaijani đŸ‡ĻđŸ‡ŋ | Bashkir 🇷đŸ‡ē | | Basque đŸ‡Ē🇸 | Belarusian 🇧🇾 | Bengali 🇧🇩 | Bosnian 🇧đŸ‡Ļ | | Breton đŸ‡Ģ🇷 | Bulgarian 🇧đŸ‡Ŧ | Burmese 🇲🇲 | Castilian đŸ‡Ē🇸 | | Catalan đŸ‡Ē🇸 | Chinese 🇨đŸ‡ŗ | Croatian 🇭🇷 | Czech 🇨đŸ‡ŋ | | Danish 🇩🇰 | Dutch đŸ‡ŗ🇱 | English đŸ‡ē🇸 | Estonian đŸ‡ĒđŸ‡Ē | | Faroese đŸ‡Ģ🇴 | Finnish đŸ‡Ģ🇮 | Flemish 🇧đŸ‡Ē | French đŸ‡Ģ🇷 | | Galician đŸ‡Ē🇸 | Georgian đŸ‡ŦđŸ‡Ē | German 🇩đŸ‡Ē | Greek đŸ‡Ŧ🇷 | | Gujarati 🇮đŸ‡ŗ | Haitian 🇭🇹 | Hausa đŸ‡ŗđŸ‡Ŧ | Hawaiian đŸ‡ē🇸 | | Hebrew 🇮🇱 | Hindi 🇮đŸ‡ŗ | Hungarian 🇭đŸ‡ē | Icelandic 🇮🇸 | | Indonesian 🇮🇩 | Italian 🇮🇹 | Japanese đŸ‡¯đŸ‡ĩ | Javanese 🇮🇩 | | Kannada 🇮đŸ‡ŗ | Kazakh 🇰đŸ‡ŋ | Khmer 🇰🇭 | Korean 🇰🇷 | | Lao 🇱đŸ‡Ļ | Latin đŸ‡ģđŸ‡Ļ | Latvian 🇱đŸ‡ģ | Lingala 🇨🇩 | | Lithuanian 🇱🇹 | Luxembourgish 🇱đŸ‡ē | Macedonian 🇲🇰 | Malagasy 🇲đŸ‡Ŧ | | Malay 🇲🇾 | Malayalam 🇮đŸ‡ŗ | Maltese 🇲🇹 | Maori đŸ‡ŗđŸ‡ŋ | | Marathi 🇮đŸ‡ŗ | Moldavian 🇲🇩 | Mongolian 🇲đŸ‡ŗ | Myanmar 🇲🇲 | | Nepali đŸ‡ŗđŸ‡ĩ | Norwegian đŸ‡ŗ🇴 | Occitan đŸ‡Ģ🇷 | Panjabi 🇮đŸ‡ŗ | | Pashto đŸ‡ĻđŸ‡Ģ | Persian 🇮🇷 | Polish đŸ‡ĩ🇱 | Portuguese đŸ‡ĩ🇹 | | Punjabi 🇮đŸ‡ŗ | Romanian 🇷🇴 | Russian 🇷đŸ‡ē | Sanskrit 🇮đŸ‡ŗ | | Serbian 🇷🇸 | Shona đŸ‡ŋđŸ‡ŧ | Sindhi đŸ‡ĩ🇰 | Sinhala 🇱🇰 | | Slovak 🇸🇰 | Slovenian 🇸🇮 | Somali 🇸🇴 | Spanish đŸ‡Ē🇸 | | Sundanese 🇮🇩 | Swahili 🇰đŸ‡Ē | Swedish 🇸đŸ‡Ē | Tagalog đŸ‡ĩ🇭 | | Tajik đŸ‡šđŸ‡¯ | Tamil 🇮đŸ‡ŗ | Tatar 🇷đŸ‡ē | Telugu 🇮đŸ‡ŗ | | Thai 🇹🇭 | Tibetan 🇨đŸ‡ŗ | Turkish 🇹🇷 | Turkmen 🇹🇲 | | Ukrainian đŸ‡ēđŸ‡Ļ | Urdu đŸ‡ĩ🇰 | Uzbek đŸ‡ēđŸ‡ŋ | Vietnamese đŸ‡ģe | | Welsh 🏴ķ §ķ ĸķ ˇķ Ŧķ ŗķ ŋ | Yiddish 🇮🇱 | Yoruba đŸ‡ŗđŸ‡Ŧ | |
--- ## 🔧 Troubleshooting
đŸ”Ĩ App crashes on start
The underlying engine requires standard C++ libraries. Install the Microsoft Visual C++ Redistributable (2015-2022).
🐌 "Simulate Typing" is slow
Some apps (games, RDP) can't handle supersonic input. Go to Settings and lower the Typing Speed to ~1200 CPM.
🎤 No Audio / Silence
The agent listens to the Default Communication Device. Ensure your microphone is set correctly in Windows Sound Settings.
---
### ⚖ī¸ PUBLIC DOMAIN (CC0 1.0) *No Rights Reserved. No Gods. No Managers.* Credit to **OpenAI** (Whisper), **Systran** (Faster-Whisper), and **Silero** (VAD).