I’m using my Google nests to give me a response to my custom responses with Assist, and it’s mostly working great. However, one thing I’m really missing is the ability to send the ‘Sorry, I couldn’t understand that’ response to a chosen Google nest, if the intent is not understood.
Does anyone know how I can pick up on a trigger when my Assist intent is not understood? Or any other way I can create some code, which would allow a nest speaker to respond, when an intent is not understood?
When looking at the pipeline debug, I can see this (from a test, where I asked my satellite what its name was):
stage: done
run:
pipeline: 01hddxq3wpnqvhc86m0v50yknw
language: en
events:
- type: run-start
data:
pipeline: 01hddxq3wpnqvhc86m0v50yknw
language: en
timestamp: "2023-10-31T09:37:58.561814+00:00"
- type: wake_word-start
data:
entity_id: wake_word.openwakeword
metadata:
format: wav
codec: pcm
bit_rate: 16
sample_rate: 16000
channel: 1
timeout: 5
timestamp: "2023-10-31T09:37:58.562155+00:00"
- type: wake_word-end
data:
wake_word_output:
wake_word_id: hey_jarvis_v0.1
timestamp: 1010
timestamp: "2023-10-31T09:38:00.627020+00:00"
- type: stt-start
data:
engine: cloud
metadata:
language: en-GB
format: wav
codec: pcm
bit_rate: 16
sample_rate: 16000
channel: 1
timestamp: "2023-10-31T09:38:00.627799+00:00"
- type: stt-vad-start
data:
timestamp: 1655
timestamp: "2023-10-31T09:38:01.903251+00:00"
- type: stt-vad-end
data:
timestamp: 2145
timestamp: "2023-10-31T09:38:02.879992+00:00"
- type: stt-end
data:
stt_output:
text: What's your name?
timestamp: "2023-10-31T09:38:03.028066+00:00"
- type: intent-start
data:
engine: homeassistant
language: en
intent_input: What's your name?
conversation_id: null
device_id: 1e867f45ccbf9dafe328c590ebcc1c06
timestamp: "2023-10-31T09:38:03.028249+00:00"
- type: intent-end
data:
intent_output:
response:
speech:
plain:
speech: Sorry, I couldn't understand that
extra_data: null
card: {}
language: en
response_type: error
data:
code: no_intent_match
conversation_id: null
timestamp: "2023-10-31T09:38:03.121658+00:00"
- type: tts-start
data:
engine: cloud
language: en-GB
voice: LibbyNeural
tts_input: Sorry, I couldn't understand that
timestamp: "2023-10-31T09:38:03.121946+00:00"
- type: tts-end
data:
tts_output:
media_id: >-
media-source://tts/cloud?message=Sorry,+I+couldn't+understand+that&language=en-GB&voice=LibbyNeural&audio_output=mp3
url: >-
/api/tts_proxy/dae2cdcb27a1d1c3b07ba2c7db91480f9d4bfd8f_en-gb_8732e2c0b4_cloud.mp3
mime_type: audio/mpeg
timestamp: "2023-10-31T09:38:03.122343+00:00"
- type: run-end
data: null
timestamp: "2023-10-31T09:38:03.124444+00:00"
wake_word:
entity_id: wake_word.openwakeword
metadata:
format: wav
codec: pcm
bit_rate: 16
sample_rate: 16000
channel: 1
timeout: 5
done: true
wake_word_output:
wake_word_id: hey_jarvis_v0.1
timestamp: 1010
stt:
engine: cloud
metadata:
language: en-GB
format: wav
codec: pcm
bit_rate: 16
sample_rate: 16000
channel: 1
done: true
stt_output:
text: What's your name?
intent:
engine: homeassistant
language: en
intent_input: What's your name?
conversation_id: null
device_id: 1e867f45ccbf9dafe328c590ebcc1c06
done: true
intent_output:
response:
speech:
plain:
speech: Sorry, I couldn't understand that
extra_data: null
card: {}
language: en
response_type: error
data:
code: no_intent_match
conversation_id: null
tts:
engine: cloud
language: en-GB
voice: LibbyNeural
tts_input: Sorry, I couldn't understand that
done: true
tts_output:
media_id: >-
media-source://tts/cloud?message=Sorry,+I+couldn't+understand+that&language=en-GB&voice=LibbyNeural&audio_output=mp3
url: >-
/api/tts_proxy/dae2cdcb27a1d1c3b07ba2c7db91480f9d4bfd8f_en-gb_8732e2c0b4_cloud.mp3
mime_type: audio/mpeg
Is there anything in here, that can be copied into a similar intent_script below (below example from one of my custom responses)?
intent_script:
DoorsWindows:
speech:
text: "The doors and windows are {{states('sensor.doors_windows_state')}}"
action:
service: "tts.google_translate_say"
data:
message: "The doors and windows are {{states('sensor.doors_windows_state')}}"
target:
entity_id: >
{{ states('sensor.choose_speaker_cmd') }}