08118cc650
- Context windows (contexts/*.yaml) scope answers to a defined domain - Optional DuckDuckGo web search behind ai.web_search.enabled (default off) - Stream partial answers into the overlay at first-token time - Default Whisper to local base.en (~9x faster); offline model loading - Priority-ordered loopback detection (BlackHole > Teams device) - Overlay: drag interior to move, edges to resize - Stop tracking model binaries (models/ is gitignored) - README/CLAUDE.md overhaul + tracked config.example.yaml Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
66 lines
3.0 KiB
YAML
66 lines
3.0 KiB
YAML
# Meeting Assistant configuration — copy to config.yaml and edit.
|
|
# (config.yaml is gitignored; it may hold machine-specific/private settings.)
|
|
|
|
audio:
|
|
sample_rate: 16000
|
|
chunk_duration: 2.0
|
|
vad_threshold: 0.5
|
|
# Transcription model (local dirs load fully offline — no Hugging Face access
|
|
# at runtime). base.en is ~9x faster than medium.en on CPU (~0.3s vs ~2.9s per
|
|
# clip) and is the main latency fix. Switch to models/whisper-medium.en for
|
|
# more robustness to noise/accents (slower).
|
|
whisper_model: models/whisper-base.en
|
|
language: en
|
|
# "push_to_talk" (hold the key, release to answer) or "continuous" (auto-listen).
|
|
# Toggle at runtime with ctrl+shift+m.
|
|
capture_mode: push_to_talk
|
|
ptt_key: alt_r # push-to-talk key (Right Option). e.g. cmd_r, f8, ctrl_r
|
|
source: both # "microphone", "system", or "both"
|
|
mic_device: null # null = auto. Or a device index / name substring.
|
|
system_device: null # null = auto-detect loopback. Or index / name.
|
|
# Devices to try (in priority order) as the "system" source that hears OTHER
|
|
# participants. A true loopback (BlackHole/Soundflower/VB-Cable) carries ALL
|
|
# system audio — works for Google Meet, Zoom, Teams, anything. "teams audio"
|
|
# is Microsoft Teams' own virtual device: zero-install but Teams-only, and it
|
|
# may be silent outside screen-share; treat it as an experiment.
|
|
loopback_keywords: ["blackhole", "soundflower", "vb-cable", "loopback", "teams audio"]
|
|
# Which speakers trigger an answer (others still add transcript context).
|
|
answer_sources: ["system", "microphone"]
|
|
# Incremental transcription while the push-to-talk key is held. Off by default:
|
|
# faster-whisper pads every call to a fixed 30s window, so on small/fast models
|
|
# this barely helps and can drop words at chunk seams. Enable only with a
|
|
# large/slow model where the per-call cost is worth amortizing during the hold.
|
|
streaming_transcription: false
|
|
# Bias Whisper toward your meeting's vocabulary (optional):
|
|
# transcription_prompt: "A software engineering interview about Python and Flask."
|
|
|
|
screen:
|
|
capture_key: ctrl+shift+space # press, then drag a box over an on-screen question
|
|
|
|
hotkeys:
|
|
toggle_overlay: ctrl+shift+h
|
|
meeting_summary: ctrl+shift+s
|
|
toggle_listening: ctrl+shift+m
|
|
|
|
ai:
|
|
context_window: 2048
|
|
max_history: 10
|
|
model: Qwen2.5-VL-7B-Instruct-Q4_K_M.gguf
|
|
mmproj: mmproj-Qwen2.5-VL-7B-Instruct-f16.gguf # required for screen reading
|
|
answer_mode: auto_obvious # auto_obvious | auto_all | suggest_only
|
|
user_name: you
|
|
# Pin the active context window by file name (contexts/<name>.yaml). If unset,
|
|
# the first contexts/*.yaml with `active: true` is used.
|
|
# active_context: python_flask_backend
|
|
# Optional web search to ground factual answers in current information.
|
|
# PRIVACY: when enabled, the question text is sent to DuckDuckGo — this
|
|
# breaks the otherwise fully on-device guarantee. Off by default.
|
|
web_search:
|
|
enabled: false
|
|
max_results: 3
|
|
timeout: 6.0
|
|
|
|
overlay:
|
|
position: top-right
|
|
font_size: 14
|