Getting Started with Hablará
From installation to first analysis in 5 minutes
Hablará runs fully offline – no cloud account needed. whisper.cpp transcribes locally, Ollama analyses locally. OpenAI and Anthropic are optional cloud providers.
At a Glance
- Download
- Permissions
- Language Model
- AI Provider
- Done
Download & Install
macOS
Apple Silicon & Intel
Windows
Windows 10/11
Linux
x64 & ARM64
First Launch
Choose Language
15 languages available, auto-detected from system language.
Permissions
Grant microphone access and set up hotkey Ctrl+Shift+D.
Storage Location
Recordings stored locally.
App Store: select folder manually.
Set Up Language Model
whisper.cpp runs locally – no internet needed. The model is downloaded once (~574 MB). Auto-selected based on language setting (q8_0).
German Turbo
~574 MBOptimised for German. Fastest option for German transcriptions.
🌐 German
Large V3 Turbo
~574 MBUniversal model for 13 languages. Best balance of quality and speed.
🌐 13 languages
Kotoba V2
~574 MBLanguage-optimised for Japanese.
🌐 Japanese
ℹ️ Optional – can be set up later in Settings.
Choose AI Provider
Ollama
Fully offline – runs locally on your device, install via shell script.
🍎 macOS
curl -fsSL https://raw.githubusercontent.com/fidpa/hablara/main/scripts/setup-ollama-mac.sh | bash 🪟 Windows
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/fidpa/hablara/main/scripts/setup-ollama-win.ps1" -OutFile "$env:TEMP\setup-ollama-win.ps1"; & "$env:TEMP\setup-ollama-win.ps1" 🐧 Linux
curl -fsSL https://raw.githubusercontent.com/fidpa/hablara/main/scripts/setup-ollama-linux.sh | bash Mistral
Cloud-based – EU-native (Paris), GDPR-compliant without SCCs, API key required.
Create API Key →🔐 API keys are stored encrypted in the OS keychain. Cloud usage requires GDPR consent in the app.
Ready to go!
Press hotkey Ctrl+Shift+D or click the record button in the app.