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
1
vote
0 answers

AWS Transcribe Post call Analytics

I'm trying to start a AWS Transcribe Post Call Analytics job from a Lambda function. I need to apply few custom categories(content match, sentiment analysis) to the starting job. I have already categories. Not sure how to apply these categories…
1
vote
0 answers

How do I create real time transcript of video call?

We are using twilio video call in our application. Need to create real time transcript of that video call. Twilio audio recording creates separate audio file for each participant and so by using AWS transcribe for transcription, it creates 2…
1
vote
1 answer

AWS Transcribe service outputs a file with access denied, even with permissions set

I am testing the AWS transcribe service for a project, after runing the start transcritpion job var TrsSession *transcribeservice.TranscribeService func TranscribeTest() (trsOutput *transcribeservice.StartTranscriptionJobOutput, err error) { …
1
vote
1 answer

How to get the credentials using only Cognito Identity pool?

I'm looking to get temporary AWS credentials through the Cognito Identity pool. And then that credentials should access the AWS Transcribe service. I've created an Identity pool and checked the option of unauthenticated user, so that I don't have to…
1
vote
0 answers

How to get temporary credentials from AWS cognito to use in AWS transcribe service

Use Case:- I have a frontend that is calling Amazon Transcribe service. I'm using s3 as deployment so can't expose the amazon credentials(access_key and secret_key) on front end. So I created a backend endpoint and want to call Cognito service to…
1
vote
0 answers

Amazon Transcribe Python API: Event handler processes audio only after the stream ends

(Didn't get answer in AWS re-post, so trying here) I am sending streaming audio data from web browser as a blob via websocket. In backend, I am using Django Channels' AsyncWebsocketConsumer to receive it, then send it to Amazon Transcribe and…
1
vote
0 answers

AWS transcribe speaker diarization, segments single speaker sentences into multiple different speakers

A bit of context, we have been using AWS Transcribe for English transcription since last one year. When the number of speakers is unknown, transcribe asks you to provide max number of speakers, by default we are passing 5. Since last month we…
1
vote
0 answers

How to use AWS Polly with streaming transcription and translate to get real-time audio translation?

I want to implement audio translation to a conference web app. I am thinking about using three AWS services for this (streaming transcribe, translate and Polly). All the examples provided in AWS documentation are based on a single line of text being…
1
vote
1 answer

Get subtitles in aws transcribe job

I am creating a function which gets the transcription output from aws transcribe job. def get_text(job_name, file_uri): job_name = job_name file_uri = file_uri transcribe_client = boto3.client('transcribe') max_tries = 60 while…
1
vote
0 answers

Amazon Transcribe: transcribe multiple languages in the same media file

I've a video file in which the speaker is speaking in more than one language (e.g. English and Italian). I want my subtitles/transcriptions to contain text in both of these languages. After reading the docs, I came to know that Amazon Transcribe…
Osama Bin Saleem
  • 779
  • 1
  • 12
  • 24
1
vote
1 answer

how to create subtitles from aws transcribe

I'm using AWS SDK for python (boto3) and want to set the subtitle output format (i.e. SRT). When I use this code, I get the error below which mentioned parameter Subtitle is not a valid parameter but according to AWS Documentation, I should be able…
1
vote
0 answers

Live transcription using AWS Transcribe

I'm working on a project that requires a live audio to be transcribed in real-time. I tried the AWS Transcribe with WebSockets using their starter code available on GitHub. Currently, for testing I have an audio file from a YouTube which I'm…
1
vote
1 answer

is it possible to map people to transcript with AWS transcribe?

I need to use some transcription service to transcribe speech. I recieve very good results with AWS transcribe. But i also need to know which person says what. Is this possible with AWS transcribe? I cannot find anything about this. ex. what i get…
1
vote
2 answers

How to use the AWS Transcribe javascript sdk

I am trying to use the @aws-sdk/client-transcribe-streaming in an Angular project, without any luck. The below code is the only example provided by AWS // ES6+ example import { TranscribeStreamingClient, StartStreamTranscriptionCommand, } from…
Skeird
  • 173
  • 2
  • 10
1
vote
1 answer

Unable to decode network response from AWS

I'm trying to setup a websocket for AWS transcribe, but I've been stuck for over a day trying to decode the byte data / Uint8ArrayView that I receive as a response. Any help is very much appreciated, I've tried tons of decoding, ByteBuffers, etc,…
1 2
3
9 10