# mavwaked — always-on listening, on workpc where the microphone is.
#
# User unit, beside mavgpud.service and maven-voice-tunnel.service. It is a
# user unit because it needs his ALSA session and his ssh agent, and because
# it should stop when he logs out.
#
# The keyword is "Мэйвен" and the three -wake- flags are what require it
# (V-487 stage two). Without them anything spoken near the fifine becomes a
# turn, which voiceSender makes safe rather than expensive: it sends
# Surface=SurfaceVoice, capping every command at L0. That does not stop her
# answering out loud, which is the whole reason the keyword exists.
#
# The threshold is 0.999 and it is the binary's default, so it is not passed.
# It came from 65 minutes of held-out Russian speech through this same binary:
# 0.9 false wakes an hour against 2.8 at 0.99, for one lost render out of 126
# (docs/evals/2026-08-09-wake-word.md). If the room proves noisier than the
# corpus, read the scores out of this unit's journal and pass -wake-threshold.
# Do not lower it by guessing.
#
# A keyword shorter than 1.32s can be heard too late to be used, because the
# head scores 1.28s of audio and the VAD has closed the utterance by then.
# "Мэйвен, <request>" is unaffected. A bare "Мэйвен" is the case that fails.
#
# -vad-model is passed on purpose. Silero answers "is this frame speech" where
# the energy floor answers "is this frame loud". It declines white noise at
# the same RMS 0 frames to 68-99, and still hears all four spoken fixtures
# (docs/evals/2026-08-09-silero-vad.md). It costs 509us a frame, 1.7% of one
# core, and never touches the GPU. Drop the flag and the energy floor is back.
#
# -barge-in is NOT passed. The threshold is room-specific and this room has no
# number yet. Turn it on only after reading the "suppressed while speaking"
# means out of this unit's own journal, never by guessing.
#
#   install: cp to ~/.config/systemd/user/ on workpc
#            systemctl --user enable --now mavwaked.service

[Unit]
Description=Maven always-on listening (silero VAD, "Мэйвен" keyword)
# The tunnel is the only path to mavend and the only thing authenticating it.
Requires=maven-voice-tunnel.service
After=maven-voice-tunnel.service

[Service]
# The Scarlett Solo 4th Gen, and not the fifine. The fifine was the device
# here for three days and mavwaked never logged one utterance in them, because
# it returns RMS 0.00004 with its capture switch on and its ALSA volume at the
# full 496 of 496. That silence is in the hardware, so no flag reaches it.
#
# Named CARD=Gen and not card 4, because a USB card number moves when
# something else is replugged and this daemon must not change ears quietly.
# Not "default" either: that follows whatever pipewire last decided.
#
# plughw and not hw. mavwaked asks arecord for 16kHz mono, which is what the
# whole pipeline is canonical in. Neither microphone offers it, so bare hw
# dies on "Channels count non available" before a frame is read. plughw puts
# ALSA's downmix and resampler in front. Any replacement wants the same.
#
# The Scarlett measured RMS 0.003 against 0.14 on the onboard input, so its
# front-panel gain is the thing to raise if she mishears. That is a knob, not
# a control ALSA exposes. The two loud devices, the onboard ALC897 and the
# camera, both clip at peak 1.0 and are worse candidates, not better ones.
Environment=LD_LIBRARY_PATH=%h/.local/lib
ExecStart=%h/.local/bin/mavwaked \
  -device plughw:CARD=Gen,DEV=0 \
  -addr 127.0.0.1:9100 \
  -lang ru \
  -vad-model %h/.local/share/maven/models/silero_vad.onnx \
  -wake-model %h/.local/share/maven/models/maven_wakeword.onnx \
  -wake-mel %h/.local/share/maven/models/melspectrogram.onnx \
  -wake-embed %h/.local/share/maven/models/embedding_model.onnx \
  -onnx-lib %h/.local/lib/libonnxruntime.so
Restart=on-failure
RestartSec=5

[Install]
WantedBy=default.target