aman/README.md

115 lines
2.6 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`
- 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
```
## Config
Create `~/.config/lel/config.json`:
```json
{
"hotkey": "Cmd+m",
"ffmpeg_input": "pulse:default",
"ffmpeg_path": "",
"whisper_model": "base",
"whisper_lang": "en",
"whisper_device": "cpu",
"record_timeout_sec": 120,
"injection_backend": "clipboard",
"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
}
```
Env overrides:
- `WHISPER_MODEL`, `WHISPER_LANG`, `WHISPER_DEVICE`
- `WHISPER_FFMPEG_IN`
- `LEL_RECORD_TIMEOUT_SEC`, `LEL_HOTKEY`, `LEL_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_CONTEXT_PROVIDER`, `LEL_CONTEXT_ON_FOCUS_CHANGE`
## 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.
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
```