Can we use Amazon Lex just to convert text from voice and pass the text input to our lambda function?
I want to capture the whole user speech and get it converted into text and further, want to process that text in my lambda function.
The answer really depends on how much speech you intend to collect from Lex to pass over to Lambda. If you want to send full recordings of speech to be converted into text, I would recommend looking at the Amazon Transcribe service first.
If you are looking to just collect simple speech, you can configure an intent in Lex to match an utterance. Then prompt the user for additional speech information using slots as seen below. This example has a prompt asking for the user's name and then inserts it into a slot called "Name".
From there, just setup the Fulfillment on the Intent to point to your Lambda function as seen below where I pass this information to a Lambda function called "LEX_CollectSpeech".
You can find the Lambda documentation that outlines the expected input from Lex and Response formats here. https://docs.aws.amazon.com/lex/latest/dg/lambda-input-response-format.html
Related
I have a Sumerian Host that acts basically as a front-end for a Lex chatbot.
However, in some cases, I need to to some processing based on the actual user utterance (that is, the text of what the user says). Is there a way I can use "Send Audio to Lex" action (or a different one) to get a text version of the user audio (so, to perform speech-to-text)?
I'm trying to use Go to send objects in a S3 bucket to Textract and collect the response.
I'm using the aws go sdk package and able to connect to my S3 bucket and list all the objects contained within. So far so good. I now need to be able to send one of those objects (a .pdf file) to Textract and collect the response(s).
The AWS Go SDK content for interacting with Textract seem to be quite extensive but I cannot find a good example for how to do this.
I would be very grateful for a sample or advice on how to do this.
To start a job, you invoke StartDocumentTextDetection, using a DocumentLocation to specify the file, and you specify a SNS topic where Textract will publish a notification when it has finished to process your job.
You have now two possibilities:
Subscribe to the SNS topic, and when you receive a message retrieve the result
Create a lambda function triggered by the SNS topic, which retrieves the result.
The second option is IMO better 'cause it use less computation time (doesn't run until the job hasn't finished).
To retrieve the job, you use GetDocumentTextDetection
If anyone else reaches this site searching for an answer:
I understood the documentation as if I could just call the StartDocumentAnalysis function through the textract SDK but in fact what was missing is the fact that you need to create a new Session first and do the calls based on the session:
https://docs.aws.amazon.com/sdk-for-go/api/service/textract/#New
I have a couple hundred transcribed results in aws transcribe and I would like to get all the transcribed text and store it in one file.
Is there any way to do this without clicking on each transcribed result and copy and pasting the text?
You can do this via the AWS APIs.
For example, if you were using Python, you can use the Python boto3 SDK:
list_transcription_jobs() will return a list of Transcription Job Names
For each job, you could then call get_transcription_job(), which will provide the TranscriptFileUri that is the location where the transcription is stored.
You can then use get_object() to download the file from Amazon S3
Your program would then need to combine the content from each file into one file.
See how you go with that. If you run into any specific difficulties, post a new Question with the code and an explanation of the problem.
I put an example on GitHub that shows how to:
run an AWS Transcribe job,
use the Requests package to get the output,
write output to the console.
You ought to be able to refit if pretty easily for your purposes. Here's some of the code, but it'll make more sense if you check out the full example:
job_name_simple = f'Jabber-{time.time_ns()}'
print(f"Starting transcription job {job_name_simple}.")
start_job(
job_name_simple, f's3://{bucket_name}/{media_object_key}', 'mp3', 'en-US',
transcribe_client)
transcribe_waiter = TranscribeCompleteWaiter(transcribe_client)
transcribe_waiter.wait(job_name_simple)
job_simple = get_job(job_name_simple, transcribe_client)
transcript_simple = requests.get(
job_simple['Transcript']['TranscriptFileUri']).json()
print(f"Transcript for job {transcript_simple['jobName']}:")
print(transcript_simple['results']['transcripts'][0]['transcript'])
I have setup a rule in cloudwatch to monitor Glue ETL. In the state change I am sending a notification to SNS. I have modified the input transformer to get a custom body of the email but not getting how to change the subject line of the email . It still giving the default "AWS Notification Message"
My Input transformer :
{"state":"$.detail.state"}
"The JOB has changed state to <state>."
Use a Lambda function—rather than the Amazon SNS topic—as a target for the CloudWatch Events rule. Then, configure the Lambda function to publish a custom message to the Amazon SNS topic when triggered by the CloudWatch Events rule.
Documented here: https://aws.amazon.com/premiumsupport/knowledge-center/change-sns-email-for-cloudwatch-events/
Transformer (no way Jose)
As far as I can tell there is currently no way to control the email subject with a transformer. Typically you will control the notification body for a rule through the transformer which modifies the input json message (e.g. in the case of a build https://docs.aws.amazon.com/codebuild/latest/userguide/sample-build-notifications.html#sample-build-notifications-ref ). Based on what I see in the documentation this only modifies part of the body embedded between the header and the footer of the email payload.
JSON (also not possible)
1. Since all notifications are generated with an API call with json payload you can experiment and configure. Using the CLI you can specify a json format using --message-structure attribute. However the subject is not part of the json payload itself and is sent as a separate parameter "--subject" (see example below) you won't be able to configure that unless they either modify the UI or the json payload.
2.In order to exercise greater control over your output you might have to use JSON (select "Constant (JSON text)") which is documented for mobile messaging https://docs.aws.amazon.com/sns/latest/dg/mobile-push-send-custommessage.html but not very well for HTTP https://docs.aws.amazon.com/sns/latest/dg/sns-message-and-json-formats.html but decent for the CLI https://docs.aws.amazon.com/cli/latest/reference/sns/publish.html
3. You can go to the console https://console.aws.amazon.com/sns/v2/ and click on "Publish a Message" which allows you to specify a subject. Notice that there is a "JSON message generator" but that's only for the body.
Coding Workaround (possible ...kinda)
If you feel really determined you can explore a workaround: look at the API and figure out what call is equivalent to sending a call which includes a subject. Create a lambda function that executes that call. From the rule invoke the lambda :-) and you are done. If there is will, there is a way...
Notes:
aws sns publish --topic-arn arn:aws:sns:us-east-1:652499160872:DP-Build --message-structure json --subject "Test Build subject" --message "{ \"default\":\"Foo\", \"email\":\"Bar\"}"
According to the docs there is a "Subject" key you can pass as a parameter:
Blockquote
Subject
The Subject parameter specified when the notification was published to the topic. Note that this is an optional parameter. If no Subject was specified, then this name/value pair does not appear in this JSON document.
Blockquote
set "detail-type":"Glue ETL State-change Notification"
you might need to look at https://docs.aws.amazon.com/AmazonCloudWatch/latest/events/CloudWatch-Events-Input-Transformer-Tutorial.html
I'm a newbie rails programmer, and I have even less experience with all the AWS products. I'm trying to use lambda to subscribe to and consume an rss feed from youtube. I am able to send the subscription request just fine with HTTParty from my locally hosted rails app:
query = {'hub.mode':'subscribe', 'hub.verify':'sync', 'hub.topic': 'https://www.youtube.com/feeds/videos.xml?channel_id=CHANNELID', 'hub.callback':'API Endpoint for Lambda'}
subscribe = 'HTTParty.post(https://pubsubhubbub.appspot.com/subscribe, :query=>query)
and it will ping the lambda function with a get request. I know that I need to echo back a hub.challenge string, but I don't know how. The lambda event is empty, I didn't see anything useful in the context. I tried formatting the response in the API gateway but that didn't work either. So right now when I try to subscribe I get back a 'Challenge Mismatch' error.
I know this: https://pubsubhubbub.googlecode.come/git/pubsubhubbub-core-0.3.html#subscribing explains what I'm trying to do better than what I just did, and section 6.2.1 is where the breakdown is. How do I set up either the AWS Lambda function and/or the API Gateway to reflect back the 'hub.challenge' verification token string?
You need to use the parameter mapping functionality of API Gateway to map the parameters from the incoming query string to a parameter passed to your Lambda function. From the documentation link you provided, it looks like you'll at least need to map the hub.challenge query string parameter, but you may also need the other parameters (hub.mode, hub.topic, and hub.verify_token) depending on what validation logic (if any) that you're implementing.
The first step is to declare your query string parameters in the method request page. Once you have declared the parameters open the integration request page (where you specify which Lambda function API Gateway should call) and use the "+" icon to add a new template. In the template you will have to specify a content type (application/json), and then the body you want to send to Lambda. You can read both query string and header parameters using the params() function. In that input mapping field you are creating the event body that is posted to AWS Lambda. For example: { "challenge": "$input.params('hub.challenge')" }
Documentation for mapping query string parameters