I want to access this “transcript” field to put it as content in my googledoc, but I can’t seem to be able to access it?
Any help? Really desperate here.
Hi @Zakoian ,
As your data structure is complex, if it’s possible, could you attach the output bundle?
It will avoid untested answer.
2 Likes
Of course ! Here it is:
[
{
"name": "343954703841932765",
"metadata": {
"@type": "type.googleapis.com/google.cloud.speech.v1p1beta1.LongRunningRecognizeMetadata",
"progressPercent": 100,
"startTime": "2024-03-20T13:54:06.458325Z",
"lastUpdateTime": "2024-03-20T13:54:11.810816Z"
},
"done": true,
"response": {
"@type": "type.googleapis.com/google.cloud.speech.v1p1beta1.LongRunningRecognizeResponse",
"results": [
{
"alternatives": [
{
"transcript": "Bonjour je m'appelle Jérémy d'Ernestine et je me permets de vous appeler par rapport à votre papa oui bonjour je m'appelle Sabrina je m'appelle parce que mon papa il a du mal à se déplacer les la nuit il y a du mal à se déplacer et du coup on souhaitez mettre en place de l'accompagnement de lui merci",
"confidence": 0.91853076,
"words": [
{
"startTime": "0s",
"endTime": "2.300s",
"word": "Bonjour"
},
{
"startTime": "2.300s",
"endTime": "2.400s",
"word": "je"
},
{
"startTime": "2.400s",
"endTime": "2.500s",
"word": "m'appelle"
},
{
"startTime": "2.500s",
"endTime": "3s",
"word": "Jérémy"
},
{
"startTime": "3s",
"endTime": "3.600s",
"word": "d'Ernestine"
},
{
"startTime": "3.600s",
"endTime": "3.900s",
"word": "et"
},
{
"startTime": "3.900s",
"endTime": "4.100s",
"word": "je"
},
{
"startTime": "4.100s",
"endTime": "4.200s",
"word": "me"
},
{
"startTime": "4.200s",
"endTime": "4.400s",
"word": "permets"
},
{
"startTime": "4.400s",
"endTime": "4.500s",
"word": "de"
},
{
"startTime": "4.500s",
"endTime": "4.700s",
"word": "vous"
},
{
"startTime": "4.700s",
"endTime": "4.800s",
"word": "appeler"
},
{
"startTime": "4.800s",
"endTime": "5s",
"word": "par"
},
{
"startTime": "5s",
"endTime": "5.300s",
"word": "rapport"
},
{
"startTime": "5.300s",
"endTime": "5.300s",
"word": "à"
},
{
"startTime": "5.300s",
"endTime": "5.400s",
"word": "votre"
},
{
"startTime": "5.400s",
"endTime": "5.900s",
"word": "papa"
},
{
"startTime": "5.900s",
"endTime": "8.700s",
"word": "oui"
},
{
"startTime": "8.700s",
"endTime": "9.200s",
"word": "bonjour"
},
{
"startTime": "9.200s",
"endTime": "9.400s",
"word": "je"
},
{
"startTime": "9.400s",
"endTime": "9.500s",
"word": "m'appelle"
},
{
"startTime": "9.500s",
"endTime": "10.200s",
"word": "Sabrina"
},
{
"startTime": "10.200s",
"endTime": "10.300s",
"word": "je"
},
{
"startTime": "10.300s",
"endTime": "10.600s",
"word": "m'appelle"
},
{
"startTime": "10.600s",
"endTime": "10.800s",
"word": "parce"
},
{
"startTime": "10.800s",
"endTime": "11s",
"word": "que"
},
{
"startTime": "11s",
"endTime": "11.100s",
"word": "mon"
},
{
"startTime": "11.100s",
"endTime": "11.300s",
"word": "papa"
},
{
"startTime": "11.300s",
"endTime": "11.600s",
"word": "il"
},
{
"startTime": "11.600s",
"endTime": "11.700s",
"word": "a"
},
{
"startTime": "11.700s",
"endTime": "11.800s",
"word": "du"
},
{
"startTime": "11.800s",
"endTime": "11.900s",
"word": "mal"
},
{
"startTime": "11.900s",
"endTime": "12.100s",
"word": "à"
},
{
"startTime": "12.100s",
"endTime": "12.600s",
"word": "se"
},
{
"startTime": "12.600s",
"endTime": "13s",
"word": "déplacer"
},
{
"startTime": "13s",
"endTime": "13.500s",
"word": "les"
},
{
"startTime": "13.500s",
"endTime": "13.900s",
"word": "la"
},
{
"startTime": "13.900s",
"endTime": "14.200s",
"word": "nuit"
},
{
"startTime": "14.200s",
"endTime": "16.100s",
"word": "il"
},
{
"startTime": "16.100s",
"endTime": "16.100s",
"word": "y"
},
{
"startTime": "16.100s",
"endTime": "16.100s",
"word": "a"
},
{
"startTime": "16.100s",
"endTime": "16.300s",
"word": "du"
},
{
"startTime": "16.300s",
"endTime": "16.400s",
"word": "mal"
},
{
"startTime": "16.400s",
"endTime": "16.500s",
"word": "à"
},
{
"startTime": "16.500s",
"endTime": "16.600s",
"word": "se"
},
{
"startTime": "16.600s",
"endTime": "16.900s",
"word": "déplacer"
},
{
"startTime": "16.900s",
"endTime": "17.600s",
"word": "et"
},
{
"startTime": "17.600s",
"endTime": "18.100s",
"word": "du"
},
{
"startTime": "18.100s",
"endTime": "18.400s",
"word": "coup"
},
{
"startTime": "18.400s",
"endTime": "18.400s",
"word": "on"
},
{
"startTime": "18.400s",
"endTime": "19.200s",
"word": "souhaitez"
},
{
"startTime": "19.200s",
"endTime": "19.400s",
"word": "mettre"
},
{
"startTime": "19.400s",
"endTime": "19.500s",
"word": "en"
},
{
"startTime": "19.500s",
"endTime": "19.800s",
"word": "place"
},
{
"startTime": "19.800s",
"endTime": "19.900s",
"word": "de"
},
{
"startTime": "19.900s",
"endTime": "20.300s",
"word": "l'accompagnement"
},
{
"startTime": "20.300s",
"endTime": "20.600s",
"word": "de"
},
{
"startTime": "20.600s",
"endTime": "20.900s",
"word": "lui"
},
{
"startTime": "20.900s",
"endTime": "21.100s",
"word": "merci"
}
]
}
],
"resultEndTime": "22.320s",
"languageCode": "fr-fr"
},
{
"alternatives": [
{
"words": [
{
"startTime": "0s",
"endTime": "2.300s",
"word": "Bonjour",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "2.300s",
"endTime": "2.400s",
"word": "je",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "2.400s",
"endTime": "2.500s",
"word": "m'appelle",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "2.500s",
"endTime": "3s",
"word": "Jérémy",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "3s",
"endTime": "3.600s",
"word": "d'Ernestine",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "3.600s",
"endTime": "3.900s",
"word": "et",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "3.900s",
"endTime": "4.100s",
"word": "je",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.100s",
"endTime": "4.200s",
"word": "me",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.200s",
"endTime": "4.400s",
"word": "permets",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.400s",
"endTime": "4.500s",
"word": "de",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.500s",
"endTime": "4.700s",
"word": "vous",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.700s",
"endTime": "4.800s",
"word": "appeler",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "4.800s",
"endTime": "5s",
"word": "par",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "5s",
"endTime": "5.300s",
"word": "rapport",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "5.300s",
"endTime": "5.300s",
"word": "à",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "5.300s",
"endTime": "5.400s",
"word": "votre",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "5.400s",
"endTime": "5.900s",
"word": "papa",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "5.900s",
"endTime": "8.700s",
"word": "oui",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "8.700s",
"endTime": "9.200s",
"word": "bonjour",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "9.200s",
"endTime": "9.400s",
"word": "je",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "9.400s",
"endTime": "9.500s",
"word": "m'appelle",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "9.500s",
"endTime": "10.200s",
"word": "Sabrina",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "10.200s",
"endTime": "10.300s",
"word": "je",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "10.300s",
"endTime": "10.600s",
"word": "m'appelle",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "10.600s",
"endTime": "10.800s",
"word": "parce",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "10.800s",
"endTime": "11s",
"word": "que",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11s",
"endTime": "11.100s",
"word": "mon",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.100s",
"endTime": "11.300s",
"word": "papa",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.300s",
"endTime": "11.600s",
"word": "il",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.600s",
"endTime": "11.700s",
"word": "a",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.700s",
"endTime": "11.800s",
"word": "du",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.800s",
"endTime": "11.900s",
"word": "mal",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "11.900s",
"endTime": "12.100s",
"word": "à",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "12.100s",
"endTime": "12.600s",
"word": "se",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "12.600s",
"endTime": "13s",
"word": "déplacer",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "13s",
"endTime": "13.500s",
"word": "les",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "13.500s",
"endTime": "13.900s",
"word": "la",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "13.900s",
"endTime": "14.200s",
"word": "nuit",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "14.200s",
"endTime": "16.100s",
"word": "il",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.100s",
"endTime": "16.100s",
"word": "y",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.100s",
"endTime": "16.100s",
"word": "a",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.100s",
"endTime": "16.300s",
"word": "du",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.300s",
"endTime": "16.400s",
"word": "mal",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.400s",
"endTime": "16.500s",
"word": "à",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.500s",
"endTime": "16.600s",
"word": "se",
"speakerTag": 1,
"speakerLabel": "1"
},
{
"startTime": "16.600s",
"endTime": "16.900s",
"word": "déplacer",
"speakerTag": 1,
"speakerLabel": "1"
}
]
}
]
}
],
"totalBilledTime": "23s",
"requestId": "343954703841932765"
}
}
]```Please find in attachment a blueprint that extract the transcript value.
I used a JSON parser, and for the data structure I just paste your file, Make almost makes everything for you.
get_transcript.json (46.0 KB)
Hope it helps.
2 Likes
Hi Philippe,
Thanks so much for your help, unfortunately I don’t see how to make it happen.
I use the JSON Parser, and then I built the Data Structure, but what do I feed it ? I have no idea…
Any help ?
Thanks again
Hi @Zakoian ,
Sorry, I misled you a bit.
In fact, the JSON parser is used to reformat and make accessible the data you’ve sent, then the last “set variable” is used to retrieve the data (here “transcript”).
Here, the JSON is already formatted, so to get the value of the “transcript” variable:
you just have to select it in the output bundle of the Google Cloud Speech, and you will get (at least, I hope) the full path to “transcript” variable.
PBI
2 Likes
Thank you so much, I am indeed able to access the “transcript” field as an output of the JSON parser module, but I still can’t find what to put in the input “JSON string” of the JSON parser, because it seems I can’t acess the “raw” output bundle of the Google Cloud Speech… Any idea on how to do that?
Thanks again so much for the help !
Ok so actually, I just yoloed it to test something, and if I write “{{28.response.results.alternatives.transcript}}” straight up in my google doc, turns out, it works!
Thanks again for the help !
3 Likes
It is a good news, if it works.
Do not forget to change the status to “solved”.
3 Likes