Questions tagged [amazon-transcribe]

Amazon Transcribe is a speech recognition service within AWS for speech-to-text-capability. Using the Amazon Transcribe API, you can analyze audio files stored in Amazon S3 and have the service return a text file of the transcribed speech.

Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capability to their applications. Using the Amazon Transcribe API, you can analyze audio files stored in Amazon S3 and have the service return a text file of the transcribed speech.

Amazon Transcribe can be used for lots of common applications, including the transcription of customer service calls and generating subtitles on audio and video content. The service can transcribe audio files stored in common formats, like WAV and MP3, with time stamps for every word so that you can easily locate the audio in the original source by searching for the text. Amazon Transcribe is continually learning and improving to keep pace with the evolution of language.

Resources:

144 questions
0
votes
0 answers

An error occurred (BadRequestException) when calling the StartTranscriptionJob operation: The specified S3 bucket can't be accessed

Getting this error when trying to create a Transcription Job via AWS client. I have attached the following policy to the IAM user of the aws account. { "Version": "2012-10-17", "Statement": [ { "Effect": "Allow", "Action": [ …
Balaji
  • 53
  • 7
0
votes
0 answers

StartTranscriptionJob with AWS returning: "An error occurred (400) when calling the StartTranscriptionJob operation:" but no further details

I've been trying to get started with the StartTranscriptionJob with AWS and I'm receiving a "An error occurred (400) when calling the StartTranscriptionJob operation:" But not further details. This is the only response I'm…
0
votes
0 answers

How to add speaker labels in AWS Transcribe streaming websockets

I'm using the AWS Transcribe example from https://github.com/amazon-archives/amazon-transcribe-websocket-static with a simple modification on the websocket query-string to add speaker labels. The current websocket URL path and querystring are…
0
votes
0 answers

What is the true minimum duration for an AWS Transcribe input file?

According to the AWS docs, it's 500 milliseconds: https://docs.aws.amazon.com/general/latest/gr/transcribe.html#limits-amazon-transcribe But according to the error message I got from the service, it's 0.5 milliseconds: "TranscriptionJobStatus":…
fblundun
  • 987
  • 7
  • 19
0
votes
0 answers

How does the Chime SDK and Amazon Transcribe integration work in terms of cost and transcription ending

For my product I've integrated the chime sdk as our webrtc media server/meeting management and that's been great. We hooked in amazon transcribe with the built in integration. The problem is there seems to be a lot of hidden/undescribed…
dbish
  • 53
  • 8
0
votes
1 answer

Can I stop an ongoing AWS transcription job with Boto3?

I am currently working with AWS Transcribe in Python to transcribe files longer than 4 hours. I split these files into chunks and process them individually. However, if one chunk fails, I'd like to stop the transcription jobs for the other chunks…
0
votes
1 answer

How do I print the response of my get_transcription_job method, but only when it's complete?

I have a Lambda Function that starts a transcription job using a file uploaded to an s3 bucket. When the Lambda is triggered, the job is started using "start_transcription_job". I then want to print the output of "get_transcription_job" in order to…
0
votes
0 answers

How do I print a file (transcribed by AWS Transcribe) that I haven't specified an output location for?

I've made a Lambda Function, using boto3, that is triggered when I upload an audio file to my s3 bucket. The function creates a transcription job using boto3's "start_transcription_job" method. I don't specify an OutputBucketName value, meaning my…
0
votes
0 answers

Real-time transcriptionInfo

I am testing AWS's Transcribe feature. I am logged into my AWS console and navigate to "Amazon Transcribe" --> "Real-time Transcription". I click the Microphone button, and it seems to start streaming. However, I get an error message Error You are…
user1811107
  • 729
  • 3
  • 18
  • 39
0
votes
0 answers

Transcribe a text from speech and generate Audio from text

I am trying to make a user interface where a user would click a mic button and speak to it and then a live stream transcription would appear on the screen. I also need to generate an audio and play it to the user as a reply to the user's input…
0
votes
1 answer

Microphone-stream aws transcribe

i was try this with repo of aws https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/cross-services/transcribe-streaming-app it is working correctly but when i used this code into my react app it gives me…
0
votes
0 answers

How do I create single audio file of video calls? Having both participants audio in single file?

We are using twilio video call. We need to create real time transcription for this call. How shall I do that? We tried to use twilio composition api but it's taking too long. Tried twilio composition api to compose the separate audio files from each…
0
votes
1 answer

Amazon EventBridge won't send events via 2 rules nor 2 targets within one rule

Within Amazon Eventbridge, I'm listening for Transcribe events such as the following: { "source": ["aws.transcribe"], "detail-type": ["Transcribe Job State Change"], "detail": { "TranscriptionJobStatus": ["FAILED", "COMPLETED"] } } I need…
Will Taylor
  • 1,994
  • 2
  • 23
  • 36
0
votes
1 answer

Programmatically list supported languages for AWS Transcribe

AWS lists supported languages for Transcribe here: https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html Short of parsing the documentation page, is there any way to get a list of these languages…
Brad
  • 159,648
  • 54
  • 349
  • 530
0
votes
0 answers

AWS Transciber SDK for Javascript returning undefined error

I am trying to use AWS Transcriber SDK for Javascript in Angular and facing issues sending audio to AWS Transcriber WS This is the error I am facing Here is my reproducible code async createMicrophoneStream() { this.audiostream = new…