Does anyone know a guide to install VOICE ASSISTANT on an ESP32 S3 updated? Most of the videos I’ve seen have old configurations and some of the configuration is deprecated. Are there any new updated guides?
Thanks
I was just playing with and working on it this past week. This works for me with an INMP441 and Max98357. I have some packages that I use to separate common configuration but they are not related to the VA stuff
substitutions:
#pins
i2s_out_lrclk_pin: GPIO6 # LRC on Max98357
i2s_out_bclk_pin: GPIO7 # BCLK on Max98357
i2s_in_lrclk_pin: GPIO2 # WS on INMP441
i2s_in_bclk_pin: GPIO1 # SLK on INMP441
light_pin: GPIO48 # on-board LED
speaker_pin: GPIO8 # DIN on Max98357
mic_pin: GPIO4 # SD on INMP441
ota_password: <redacted>
api_key: <redacted>
ip: <redacted>
dev_name: s3test
friendly: S3Test
# Phases of the Voice AssistantGPIO8
# IDLE: The voice assistant is ready to be triggered by a wake-word
voice_assist_idle_phase_id: '1'
# LISTENING: The voice assistant is ready to listen to a voice command (after being triggered by the wake word)
voice_assist_listening_phase_id: '2'
# THINKING: The voice assistant is currently processing the command
voice_assist_thinking_phase_id: '3'
# REPLYING: The voice assistant is replying to the command
voice_assist_replying_phase_id: '4'
# NOT_READY: The voice assistant is not ready
voice_assist_not_ready_phase_id: '10'
# ERROR: The voice assistant encountered an error
voice_assist_error_phase_id: '11'
# MUTED: The voice assistant is muted and will not reply to a wake-word
voice_assist_muted_phase_id: '12'
psram:
mode: octal
speed: 80MHz
esp32:
board: esp32-s3-devkitc-1
variant: ESP32S3
framework:
type: esp-idf
version: recommended
sdkconfig_options:
# ESP32-S3 N16R8
CONFIG_ESP32_S3_BOX_BOARD: "y"
CONFIG_ESP32S3_DEFAULT_CPU_FREQ_240: "y"
CONFIG_ESP32S3_DATA_CACHE_64KB: "y"
CONFIG_ESP32S3_DATA_CACHE_LINE_64B: "y"
CONFIG_BT_ALLOCATION_FROM_SPIRAM_FIRST: "y"
CONFIG_BT_BLE_DYNAMIC_ENV_MEMORY: "y"
CONFIG_MBEDTLS_EXTERNAL_MEM_ALLOC: "y"
CONFIG_MBEDTLS_SSL_PROTO_TLS1_3: "y"
# ESP32-S3-Zero
# CONFIG_ESP32_S3_BOX_BOARD: "y"
# CONFIG_ESP32_WIFI_STATIC_RX_BUFFER_NUM: "16"
# CONFIG_ESP32_WIFI_DYNAMIC_RX_BUFFER_NUM: "512"
# CONFIG_TCPIP_RECVMBOX_SIZE: "512"
# CONFIG_TCP_SND_BUF_DEFAULT: "65535"
# CONFIG_TCP_WND_DEFAULT: "512000"
# CONFIG_TCP_RECVMBOX_SIZE: "512"
# CONFIG_ESP32S3_DEFAULT_CPU_FREQ_240: "y"
# CONFIG_ESP32S3_DATA_CACHE_64KB: "y"
# CONFIG_ESP32S3_DATA_CACHE_LINE_64B: "y"
# CONFIG_BT_ALLOCATION_FROM_SPIRAM_FIRST: "y"
# CONFIG_BT_BLE_DYNAMIC_ENV_MEMORY: "y"
# CONFIG_MBEDTLS_EXTERNAL_MEM_ALLOC: "y"
# CONFIG_MBEDTLS_SSL_PROTO_TLS1_3: "y"
packages:
common: !include common/common.yaml
wifi: !include common/static_wifi.yaml
base: !include common/esp32dev-base.yaml
esphome:
on_boot:
priority: 600
then:
# Run the script to refresh the LED status
- script.execute: control_led
# - output.turn_off: set_low_speaker
# If after 30 seconds, the device is still initializing (It did not yet connect to Home Assistant), turn off the init_in_progress variable and run the script to refresh the LED status
- delay: 30s
- if:
condition:
lambda: return id(init_in_progress);
then:
- lambda: id(init_in_progress) = false;
- script.execute: control_led
microphone:
- platform: i2s_audio
i2s_din_pin: ${mic_pin}
adc_type: external
pdm: false
i2s_audio_id: i2s_in
id: comm_mic
channel: left
speaker:
- platform: i2s_audio
id: i2s_audio_speaker
dac_type: external
sample_rate: 48000
i2s_dout_pin:
number: ${speaker_pin}
bits_per_sample: 32bit
i2s_audio_id: i2s_output
timeout: never
buffer_duration: 100ms
channel: left
# sample_rate: 16000
# bits_per_sample: 32bit
# Virtual speakers to combine the announcement and media streams together into one output
- platform: mixer
id: mixing_speaker
output_speaker: i2s_audio_speaker
num_channels: 2
source_speakers:
- id: announcement_mixing_input
timeout: never
- id: media_mixing_input
timeout: never
# Vritual speakers to resample each pipelines' audio, if necessary, as the mixer speaker requires the same sample rate
- platform: resampler
id: announcement_resampling_speaker
output_speaker: announcement_mixing_input
sample_rate: 48000
bits_per_sample: 16
- platform: resampler
id: media_resampling_speaker
output_speaker: media_mixing_input
sample_rate: 48000
bits_per_sample: 16
media_player:
- platform: speaker
id: external_media_player
name: Media Player
internal: False
volume_increment: 0.05
volume_min: 0.4
volume_max: 0.85
announcement_pipeline:
speaker: announcement_resampling_speaker
format: FLAC # FLAC is the least processor intensive codec
num_channels: 1 # Stereo audio is unnecessary for announcements
sample_rate: 48000
media_pipeline:
speaker: media_resampling_speaker
format: FLAC # FLAC is the least processor intensive codec
num_channels: 2
sample_rate: 48000
on_announcement:
- mixer_speaker.apply_ducking:
id: media_mixing_input
decibel_reduction: 20
duration: 0.0s
on_state:
if:
condition:
and:
- not:
voice_assistant.is_running:
- not:
media_player.is_announcing:
then:
- mixer_speaker.apply_ducking:
id: media_mixing_input
decibel_reduction: 0
duration: 1.0s
files:
- id: timer_finished_sound
file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/timer_finished.flac
- id: wake_word_triggered_sound
file: https://github.com/esphome/home-assistant-voice-pe/raw/dev/sounds/wake_word_triggered.flac
i2s_audio:
- id: i2s_output
i2s_lrclk_pin: ${i2s_out_lrclk_pin}
i2s_bclk_pin: ${i2s_out_bclk_pin}
- id: i2s_in
i2s_lrclk_pin: ${i2s_in_lrclk_pin}
i2s_bclk_pin: ${i2s_in_bclk_pin}
voice_assistant:
id: va
microphone: comm_mic
media_player: external_media_player
noise_suppression_level: 4
auto_gain: 31dBFS
volume_multiplier: 8
# When the voice assistant connects to HA:
# Set init_in_progress to false (Initialization is over).
# If the switch is on, start the voice assistant
# In any case: Set the correct phase and run the script to refresh the LED status
on_client_connected:
- lambda: id(init_in_progress) = false;
- if:
condition:
switch.is_on: voice_enabled
then:
- micro_wake_word.start
- lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
else:
- lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
- script.execute: control_led
# When the voice assistant disconnects to HA:
# Stop the voice assistant
# Set the correct phase and run the script to refresh the LED status
on_client_disconnected:
- lambda: id(voice_assistant_phase) = ${voice_assist_not_ready_phase_id};
- micro_wake_word.stop
- script.execute: control_led
# When the voice assistant starts to listen: Set the correct phase and run the script to refresh the LED status
on_listening:
- lambda: id(voice_assistant_phase) = ${voice_assist_listening_phase_id};
- script.execute: control_led
# When the voice assistant starts to think: Set the correct phase and run the script to refresh the LED status
on_stt_vad_end:
- lambda: id(voice_assistant_phase) = ${voice_assist_thinking_phase_id};
- script.execute: control_led
# When the voice assistant starts to reply: Set the correct phase and run the script to refresh the LED status
# on_tts_stream_start:
on_tts_start:
- lambda: id(voice_assistant_phase) = ${voice_assist_replying_phase_id};
- script.execute: control_led
on_end:
- if:
condition:
- switch.is_on: voice_enabled
then:
- wait_until:
not:
voice_assistant.is_running:
- micro_wake_word.start
# When the voice assistant finished to reply: Set the correct phase and run the script to refresh the LED status
# on_tts_stream_end:
# on_stt_end:
- lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
- script.execute: control_led
# When the voice assistant encounters an error:
# Set the error phase and run the script to refresh the LED status
# Wait 1 second and set the correct phase (idle or muted depending on the state of the switch) and run the script to refresh the LED status
on_error:
- if:
condition:
lambda: return !id(init_in_progress);
then:
- lambda: id(voice_assistant_phase) = ${voice_assist_error_phase_id};
- script.execute: control_led
- delay: 1s
- if:
condition:
switch.is_on: voice_enabled
then:
- lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
else:
- lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
- script.execute: control_led
micro_wake_word:
models:
- okay_nabu
vad:
id: mww
on_wake_word_detected:
- if:
condition:
switch.is_on: voice_enabled
then:
- if:
condition:
voice_assistant.is_running:
then:
voice_assistant.stop:
# Stop any other media player announcement
else:
- if:
condition:
media_player.is_announcing:
then:
- media_player.stop:
announcement: true
# Start the voice assistant and play the wake sound, if enabled
else:
- script.execute:
id: play_sound
priority: true
sound_file: !lambda return id(wake_word_triggered_sound);
- delay: 300ms
- voice_assistant.start:
wake_word: !lambda return wake_word;
wifi:
# If the device connects, or disconnects, to the Wifi: Run the script to refresh the LED status
on_connect:
- script.execute: control_led
on_disconnect:
- script.execute: control_led
globals:
# Global initialisation variable. Initialized to true and set to false once everything is connected. Only used to have a smooth "plugging" experience
- id: init_in_progress
type: bool
restore_value: no
initial_value: 'true'
# Global variable tracking the phase of the voice assistant (defined above). Initialized to not_ready
- id: voice_assistant_phase
type: int
restore_value: no
initial_value: ${voice_assist_not_ready_phase_id}
light:
- platform: esp32_rmt_led_strip
id: led
pin: ${light_pin}
chipset: WS2812
max_refresh_rate: 15ms
num_leds: 1
rgb_order: GRB
rmt_symbols: 192
default_transition_length: 0ms
effects:
- pulse:
name: "Slow Pulse"
transition_length: 250ms
update_interval: 250ms
min_brightness: 50%
max_brightness: 100%
- pulse:
name: "Fast Pulse"
transition_length: 100ms
update_interval: 100ms
min_brightness: 50%
max_brightness: 100%
script:
# Master script controlling the LED, based on different conditions: initialization in progress, wifi and API connected, and the current voice assistant phase.
# For the sake of simplicity and re-usability, the script calls child scripts defined below.
# This script will be called every time one of these conditions is changing.
- id: control_led
then:
- if:
condition:
lambda: return !id(init_in_progress);
then:
- if:
condition:
wifi.connected:
then:
- if:
condition:
api.connected:
then:
- lambda: |
switch(id(voice_assistant_phase)) {
case ${voice_assist_listening_phase_id}:
id(control_led_voice_assist_listening_phase).execute();
break;
case ${voice_assist_thinking_phase_id}:
id(control_led_voice_assist_thinking_phase).execute();
break;
case ${voice_assist_replying_phase_id}:
id(control_led_voice_assist_replying_phase).execute();
break;
case ${voice_assist_error_phase_id}:
id(control_led_voice_assist_error_phase).execute();
break;
case ${voice_assist_muted_phase_id}:
id(control_led_voice_assist_muted_phase).execute();
break;
case ${voice_assist_not_ready_phase_id}:
id(control_led_voice_assist_not_ready_phase).execute();
break;
default:
id(control_led_voice_assist_idle_phase).execute();
break;
}
else:
- script.execute: control_led_no_ha_connection_state
else:
- script.execute: control_led_no_ha_connection_state
else:
- script.execute: control_led_init_state
# Script executed during initialisation: In this example: Turn the LED in green with a slow pulse 🟢
- id: control_led_init_state
then:
- light.turn_on:
id: led
blue: 0%
red: 0%
green: 100%
effect: "Fast Pulse"
# Script executed when the device has no connection to Home Assistant: In this example: Turn off the LED
- id: control_led_no_ha_connection_state
then:
- light.turn_off:
id: led
# Script executed when the voice assistant is idle (waiting for a wake word): In this example: Turn the LED in white with 20% of brightness ⚪
- id: control_led_voice_assist_idle_phase
then:
- light.turn_on:
id: led
blue: 100%
red: 100%
green: 100%
brightness: 20%
effect: "none"
# Script executed when the voice assistant is listening to a command: In this example: Turn the LED in blue with a slow pulse 🔵
- id: control_led_voice_assist_listening_phase
then:
- light.turn_on:
id: led
blue: 100%
red: 0%
green: 0%
effect: "Slow Pulse"
# Script executed when the voice assistant is processing the command: In this example: Turn the LED in blue with a fast pulse 🔵
- id: control_led_voice_assist_thinking_phase
then:
- light.turn_on:
id: led
blue: 100%
red: 0%
green: 0%
effect: "Fast Pulse"
# Script executed when the voice assistant is replying to a command: In this example: Turn the LED in blue, solid (no pulse) 🔵
- id: control_led_voice_assist_replying_phase
then:
- light.turn_on:
id: led
blue: 100%
red: 0%
green: 0%
brightness: 100%
effect: "none"
# Script executed when the voice assistant encounters an error: In this example: Turn the LED in red, solid (no pulse) 🔴
- id: control_led_voice_assist_error_phase
then:
- light.turn_on:
id: led
blue: 0%
red: 100%
green: 0%
brightness: 100%
effect: "none"
# Script executed when the voice assistant is muted: In this example: Turn off the LED
- id: control_led_voice_assist_muted_phase
then:
- light.turn_off:
id: led
# Script executed when the voice assistant is not ready: In this example: Turn off the LED
- id: control_led_voice_assist_not_ready_phase
then:
- light.turn_off:
id: led
# Script executed when we want to play sounds on the device.
- id: play_sound
parameters:
priority: bool
sound_file: "audio::AudioFile*"
then:
- lambda: |-
if (priority) {
id(external_media_player)
->make_call()
.set_command(media_player::MediaPlayerCommand::MEDIA_PLAYER_COMMAND_STOP)
.set_announcement(true)
.perform();
}
if ( (id(external_media_player).state != media_player::MediaPlayerState::MEDIA_PLAYER_STATE_ANNOUNCING ) || priority) {
id(external_media_player)
->play_file(sound_file, true, false);
}
switch:
- platform: template
name: Enable Voice Assistant
id: voice_enabled
optimistic: true
restore_mode: RESTORE_DEFAULT_ON
icon: mdi:assistant
# When the switch is turned on (on Home Assistant):
# Start the voice assistant component
# Set the correct phase and run the script to refresh the LED status
on_turn_on:
- if:
condition:
lambda: return !id(init_in_progress);
then:
- lambda: id(voice_assistant_phase) = ${voice_assist_idle_phase_id};
- if:
condition:
not:
- voice_assistant.is_running
then:
- micro_wake_word.start
- script.execute: control_led
# When the switch is turned off (on Home Assistant):
# Stop the voice assistant component
# Set the correct phase and run the script to refresh the LED status
on_turn_off:
- if:
condition:
lambda: return !id(init_in_progress);
then:
- voice_assistant.stop
- micro_wake_word.stop
- lambda: id(voice_assistant_phase) = ${voice_assist_muted_phase_id};
- script.execute: control_led
6 Likes
Thanks steriku.
That code is just what I needed to update my voice setups. That saved me a lot of work.
did you try it?
I haven’t yet and I think I’ll do it this week… in my previous configuration I had many deprecated configurations
Surely one of my issues that it will fix was with the LED (rtm_symbols should fix my first issue) but I don’t know if the rest is updated or deprecated
Yep I updated my voice stuff with the code from above. I did mess about with the light section as sometimes the LED didn’t work. Not sure if it was the code or not. But it is working with this for me right now.
light:
- platform: esp32_rmt_led_strip
id: led
name: ${node_name} LED
pin: GPIO14
rgb_order: RGB
num_leds: 1
chipset: ws2812
effects:
- pulse:
name: "Slow Pulse"
transition_length: 250ms
update_interval: 250ms
min_brightness: 50%
max_brightness: 100%
- pulse:
name: "Fast Pulse"
transition_length: 100ms
update_interval: 100ms
min_brightness: 50%
max_brightness: 100%
1 Like
I have just tried updating this code with esphome 2025.4.1 and it is now no longer compiling. I get this error.
Reading CMake configuration...
-- git rev-parse returned 'fatal: not a git repository (or any parent up to mount point /)
Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).'
-- Building ESP-IDF components for target esp32s3
Processing 1 dependencies:
[1/1] idf (5.1.5)
-- Project sdkconfig file /config/.esphome/build/office-assist/sdkconfig.office-assist
-- Configuring incomplete, errors occurred!
See also "/config/.esphome/build/office-assist/.pioenvs/office-assist/CMakeFiles/CMakeOutput.log".
fatal: not a git repository (or any parent up to mount point /)
Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
/root/.platformio/penv/.espidf-5.1.5/bin/python: No module named kconfgen
CMake Error at /config/.esphome/platformio/packages/framework-espidf@src-6e6cd5244a43bdfe453daac50cfe73b6/tools/cmake/kconfig.cmake:176 (message):
Failed to run kconfgen
(/root/.platformio/penv/.espidf-5.1.5/bin/python;-m;kconfgen;--list-separator=semicolon;--kconfig;/config/.esphome/platformio/packages/framework-espidf@src-6e6cd5244a43bdfe453daac50cfe73b6/Kconfig;--sdkconfig-rename;/config/.esphome/platformio/packages/framework-espidf@src-6e6cd5244a43bdfe453daac50cfe73b6/sdkconfig.rename;--config;/config/.esphome/build/office-assist/sdkconfig.office-assist;--env-file;/config/.esphome/build/office-assist/.pioenvs/office-assist/config.env).
Error 1
Call Stack (most recent call first):
/config/.esphome/platformio/packages/framework-espidf@src-6e6cd5244a43bdfe453daac50cfe73b6/tools/cmake/build.cmake:619 (__kconfig_generate_config)
/config/.esphome/platformio/packages/framework-espidf@src-6e6cd5244a43bdfe453daac50cfe73b6/tools/cmake/project.cmake:604 (idf_build_process)
CMakeLists.txt:3 (project)
========================= [FAILED] Took 16.53 seconds =========================
Any body have any clues why this maybe happening, works fine with version 2025.3
thank you (I don’t even have a suit) for that config, made my media_player work without jitter and stuff