Skip to content

Navigation Menu

Sign in
Sign up
KNOOP edited this page Aug 27, 2026 · 3 revisions

Settings Summary & Services

Compatible with Android 5-16.

0.6.0 reorganized the main Settings into clearer subpages — Device Services, Interaction, and Browser each have their own section. Long descriptions can be expanded when needed, and layouts adapt across portrait, landscape, and unusual DPI configurations.


Settings Summary

Setting Location Description Default
Device Name Voice Config Name shown in HA device_model_voice_assistant
Port Voice Config ESPHome communication port 6053
API Encryption Key Voice Config → ESPHome Noise NNpsk0 PSK (Unlock/Encrypt/Generate) (0.7.3) Unlock
Chorus Wake Voice Config Multi-device wake arbitration (0.7.3) On
Wake Word Engine Voice Config microWakeWord (uint8 TFLite) or OpenWakeWord (native C++ streaming) microWakeWord
Wake Word 1 Voice Config Primary wake word Hey Jarvis
Wake Word 2 Voice Config Secondary wake word None
Sensitivity Voice Config Wake word sensitivity -
Wake Sound Voice Config Prompt sound when recording starts Optional
Wake Word Library Voice Config Import custom wake word models Empty
Voice Channel Voice Config Master voice input switch On
System Recording Mode Voice Config Audio capture mode Auto select
Noise suppression Voice Config Hardware noise suppressor On
Software noise suppression Voice Config WebRTC NS (mutex with hardware NS) (0.7.3) Off
NS strength Voice Config Light / Standard / Strong (0.7.3) Light
Automatic gain control Voice Config Device AGC On
Hardware echo cancellation Voice Config Hardware AEC On
Software echo cancellation Voice Config Speex/AEC3 software AEC (mutex with hardware) Off
AEC strength Voice Config Light / Standard / Strong (Speex NLP) (0.7.3) Standard
AEC room type Voice Config Small / Adaptive / Open plan (0.7.3) Adaptive
Pause AEC while speaking Voice Config Bypass software AEC during user speech (0.7.3) Off
Echo cancellation strength Voice Config Light / Standard / Strong / Adaptive (0.6.5) Adaptive+Standard
Noise/echo preview Voice Config Record and compare before/after processing (0.6.6) -
Voiceprint recognition Voice Config → Voiceprint Speaker recognition on/off Off
Voiceprint mode Voice Config → Voiceprint Manual (record 5 samples) or Automatic (passive learning) Automatic
Voiceprint User 1 name Voice Config → Voiceprint Display name for speaker 1 User 1
Voiceprint User 2 name Voice Config → Voiceprint Display name for speaker 2 User 2
Wake-word voiceprint check Voice Config → Voiceprint Restrict wake to enrolled speakers (manual mode only) Off
Audio event detection Voice Config → Audio events Local sound detection on/off Off
Audio event display duration Voice Config → Audio events How long sensor holds event label 30s
Audio event monitored types Voice Config → Audio events Which sound types to detect Speech only
Audio event sensitivity Voice Config → Audio events Detection sensitivity preset Balanced
Software Mic Gain Voice Config PCM boost -24 to +24 dB (0.6.4) 0
Audio Config Voice Config Capture preset Standard 16kHz Mono
Mute Voice Config Turn off microphone Off
Stop word Voice Config Stop-word engine: built-in DSP (no model) or any wake-engine model (0.7.3) Built-in DSP
Continuous Conversation Interaction Issue commands continuously Off
Floating Subtitle Interaction Display conversation text Off
Keep Running Service features Boot auto-start, crash recovery, screen-off CPU keep-alive (0.7.3) On
Keep CPU awake when screen is off Service features → Keep Running Prevent deep sleep so HA link stays alive (0.7.3) On
Interface scale Advanced → Settings style 75%–200% UI scale for misconfigured panels (0.7.3) 100%
Browser performance policy Display & Browser High / Adaptive / Power saver, also a HA select entity (0.7.3) Adaptive
Open apps in a window Service features → Minimal Launcher Floating app window for selected apps (0.7.3) Off

Home Assistant Services

Manually Trigger Wake

service: esphome.your_device_name_trigger_wake
data: {}

Control Mute

# Enable mute
service: switch.turn_on
target:
 entity_id: switch.your_device_name_mute
# Disable mute
service: switch.turn_off
target:
 entity_id: switch.your_device_name_mute

Set Volume

service: media_player.volume_set
target:
 entity_id: media_player.your_device_name
data:
 volume_level: 0.8 # 0.0 - 1.0

Send Voice Command (Text)

service: text.set_value
target:
 entity_id: text.your_device_name_voice_command
data:
 value: "Turn on the living room light"

FAQ

Ava can't hear me?

  1. Check if microphone permission is granted
  2. Check if mute mode is enabled
  3. Check if Voice Channel is enabled
  4. Make sure device volume isn't muted
  5. Try speaking closer to device
  6. Try a different System Recording Mode

Wake word recognition inaccurate?

  1. Try a different wake word
  2. Adjust wake word sensitivity
  3. Make sure environment isn't too noisy
  4. Enable noise suppression
  5. Speak at moderate speed, pronounce clearly
  6. Try OpenWakeWord — its shared embedding + consecutive-hit gate is more robust to noise. microWakeWord remains the lightweight always-on default.

Wake word doesn't work during music playback?

  1. Enable Software echo cancellation in Settings -> Voice Config
  2. This cancels Ava's own playback from the microphone input

Speech recognition results wrong?

This is usually a Home Assistant issue:

  1. Check HA voice assistant configuration
  2. Make sure Whisper etc. components are working
  3. Check network latency
  4. Try speaking more clearly

Back to Voice Control

Clone this wiki locally

AltStyle によって変換されたページ (->オリジナル) /