145 lines
3.8 KiB
Markdown
145 lines
3.8 KiB
Markdown
# lel
|
|
|
|
Python X11 transcription daemon that records audio, runs Whisper, logs the transcript, and can optionally run AI post-processing before injecting text.
|
|
|
|
## Requirements
|
|
|
|
- X11 (not Wayland)
|
|
- `ffmpeg`
|
|
- `faster-whisper`
|
|
- `pactl` (PulseAudio utilities for mic selection)
|
|
- Tray icon deps: `gtk3`
|
|
- i3 window manager (focus metadata via i3 IPC)
|
|
- Python deps: `pillow`, `python-xlib`, `faster-whisper`, `PyGObject`, `i3ipc`
|
|
|
|
## Python Daemon
|
|
|
|
Install Python deps:
|
|
|
|
```bash
|
|
pip install -r requirements.txt
|
|
```
|
|
|
|
Run:
|
|
|
|
```bash
|
|
python3 src/leld.py --config ~/.config/lel/config.json
|
|
```
|
|
|
|
Open settings:
|
|
|
|
```bash
|
|
python3 src/leld.py --settings --config ~/.config/lel/config.json
|
|
```
|
|
|
|
## Config
|
|
|
|
Create `~/.config/lel/config.json`:
|
|
|
|
```json
|
|
{
|
|
"hotkey": "Cmd+m",
|
|
"edit_hotkey": "Cmd+n",
|
|
"ffmpeg_input": "pulse:default",
|
|
"ffmpeg_path": "",
|
|
"whisper_model": "base",
|
|
"whisper_lang": "en",
|
|
"whisper_device": "cpu",
|
|
"record_timeout_sec": 120,
|
|
"edit_record_timeout_sec": 120,
|
|
"injection_backend": "clipboard",
|
|
"edit_injection_backend": "clipboard",
|
|
"languages": {
|
|
"en": { "code": "en", "hotkey": "Cmd+m", "label": "English" },
|
|
"ptBR": { "code": "pt-BR", "hotkey": "Cmd+b", "label": "Português (Brasil)" }
|
|
},
|
|
"edit_language_detection": { "enabled": true, "provider": "langdetect", "fallback_code": "en" },
|
|
|
|
"context_capture": {
|
|
"provider": "i3ipc",
|
|
"on_focus_change": "abort"
|
|
},
|
|
"context_rules": [
|
|
{
|
|
"tag": "terminal",
|
|
"match": { "class": "Alacritty" },
|
|
"ai_enabled": false
|
|
},
|
|
{
|
|
"tag": "chat",
|
|
"match": { "title_contains": "Slack" },
|
|
"ai_prompt_file": "/home/thales/.config/lel/prompts/slack.txt"
|
|
}
|
|
],
|
|
|
|
"ai_enabled": true,
|
|
"ai_model": "llama3.2:3b",
|
|
"ai_temperature": 0.0,
|
|
"ai_system_prompt_file": "",
|
|
"ai_base_url": "http://localhost:11434/v1/chat/completions",
|
|
"ai_api_key": "",
|
|
"ai_timeout_sec": 20,
|
|
"edit_ai_enabled": true,
|
|
"edit_ai_temperature": 0.0,
|
|
"edit_ai_system_prompt_file": "",
|
|
"edit_window": { "width": 800, "height": 400 }
|
|
}
|
|
```
|
|
|
|
Env overrides:
|
|
|
|
- `WHISPER_MODEL`, `WHISPER_LANG`, `WHISPER_DEVICE`
|
|
- `WHISPER_FFMPEG_IN`
|
|
- `LEL_RECORD_TIMEOUT_SEC`, `LEL_HOTKEY`, `LEL_INJECTION_BACKEND`
|
|
- `LEL_EDIT_RECORD_TIMEOUT_SEC`, `LEL_EDIT_HOTKEY`, `LEL_EDIT_INJECTION_BACKEND`
|
|
- `LEL_FFMPEG_PATH`
|
|
- `LEL_AI_ENABLED`, `LEL_AI_MODEL`, `LEL_AI_TEMPERATURE`, `LEL_AI_SYSTEM_PROMPT_FILE`
|
|
- `LEL_AI_BASE_URL`, `LEL_AI_API_KEY`, `LEL_AI_TIMEOUT_SEC`
|
|
- `LEL_EDIT_AI_ENABLED`, `LEL_EDIT_AI_TEMPERATURE`, `LEL_EDIT_AI_SYSTEM_PROMPT_FILE`
|
|
- `LEL_CONTEXT_PROVIDER`, `LEL_CONTEXT_ON_FOCUS_CHANGE`
|
|
- `LEL_LANGUAGES_JSON`, `LEL_EDIT_LANG_FALLBACK`
|
|
|
|
## systemd user service
|
|
|
|
```bash
|
|
mkdir -p ~/.local/bin
|
|
cp src/leld.py ~/.local/bin/leld.py
|
|
cp systemd/lel.service ~/.config/systemd/user/lel.service
|
|
systemctl --user daemon-reload
|
|
systemctl --user enable --now lel
|
|
```
|
|
|
|
## Usage
|
|
|
|
- Press the hotkey once to start recording.
|
|
- Press it again to stop and transcribe.
|
|
- The transcript is logged to stderr.
|
|
- Press the edit hotkey to open the edit window; click Apply to edit using spoken instructions.
|
|
- Default language hotkeys: English `Cmd+m`, Portuguese (Brazil) `Cmd+b`.
|
|
|
|
Edit workflow notes:
|
|
|
|
- Uses the X11 primary selection (currently selected text).
|
|
- Opens a floating GTK window with the selected text.
|
|
- Records your spoken edit instruction until you click Apply.
|
|
|
|
Injection backends:
|
|
|
|
- `clipboard`: copy to clipboard and inject via Ctrl+Shift+V (GTK clipboard + XTest)
|
|
- `injection`: type the text with simulated keypresses (XTest)
|
|
|
|
AI provider:
|
|
|
|
- Generic OpenAI-compatible chat API at `ai_base_url`
|
|
|
|
Context capture:
|
|
|
|
- `context_capture` stores the focused window at hotkey time (via i3 IPC).
|
|
- If focus changes before injection, the workflow aborts (interpreted as a cancel).
|
|
- `context_rules` lets you match on app/title and override AI/injection behavior.
|
|
|
|
Control:
|
|
|
|
```bash
|
|
make run
|
|
```
|