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
2
votes
1 answer

Access Denied error AWS Transcription Node JS API

I am using AWS transcription API on Node JS with following code const tClient = new TranscribeClient({ region: "us-east-1", credentials: { accessKeyId: AWS_ID, secretAccessKey: SECRET, } }); …
2
votes
1 answer

How to get uri path for a file stored in s3 Bucket

My Bucket name 'ABC' has a structure as follows: audiofiles audio_one.wav audio_two.mp3 I want a python code to get the URI of these files not the file or file list, the file uri so that I can use the file as the input link in the…
2
votes
1 answer

React Native record video and capture Speech to Text

I'm using React Native Camera to record video. I would also like to transcribe the voice at the same time (speech-to-text). I'm looking at React Native Voice but I don't think I can use both libraries at once (sharing the Mic input). Wondering if…
2
votes
0 answers

Capture Sound from Mirophone and speakers

We are using amazon transcribe to make speach to text but we need to capture sound from both microphone and speakers. Do you think that this can be done with sounddevice or should we use something else? amazon-transcribe-streaming-sdk Mic…
2
votes
0 answers

AWS Transcrible in Boto3

I am having a question regarding the DataAccessRoleArn setting in boto3 start_transcription_job function Here is my code below: transcribe.start_transcription_job(TranscriptionJobName=transcriptname, …
Meng Ge
  • 21
  • 1
  • 6
2
votes
0 answers

Amazon Transcribe streaming with Node.js using websocket

I am working on a whatsapp chatbot where I receive audio file(ogg format) file url from Whatsapp and I get buffer and upload that file on S3(sample.ogg) Now what is want to use AWS Transcribe Streaming so I am creating readStream of file and…
2
votes
1 answer

python aws sdk is missing transcribe streaming API

I checked github code for transcribe streaming options and it looks like there is no transcribe streaming mentions neither in docs nor in config file: src/botocore/botocore/data/transcribe/2017-10-26/service-2.json. But I see documentation for Ruby:…
2
votes
1 answer

AWS Transcribe is not recognizing the media format of my file correctly

I'm using a lambda function to receive a bytes array of audio data, save it as mp3, store it in S3, and then use the S3 object to start a Transcribe job. Everything's been processed correctly. I can see the .mp3 file in S3. I've also downloaded it…
2
votes
1 answer

AWS Translate code is throwing an unable to unmarshall error

I am trying to use AWS-translate to translate an mp3 file in an s3 bucket. Currently, I have the error below being thrown. My code is: public class ProviderTranscribeController { private static final Logger LOGGER =…
Hywel Griffiths
  • 287
  • 5
  • 16
2
votes
1 answer

AWS Transcribe | Can't create custom vocabulary using table via SDK

There are two options provided by AWS Transcribe to create a custom vocabulary. For more info Custom Vocabularies Using List Using Table I can create custom vocabularies in both ways via AWS console but when it comes to AWS Java SDK, I can create…
2
votes
2 answers

Get result from Amazon Transcribe directly (serverless)

I use serverless Lambda services to transcribe from speech to text with Amazon Transcribe. My current scripts are able to transcribe file from S3 and store the result as a JSON file also in S3. Is there a possibility to get the result directly,…
mm1975
  • 1,583
  • 4
  • 30
  • 51
2
votes
1 answer

Does AWS Lex use AWS Transcribe as the ASR for prompt recognition?

I am trying to determine if AWS Lex uses AWS Transcribe for prompt confirmations. For example, Lex asks "What's your phone number?", the user responds with "1-2-3-4". Lex then asks, "Did you say 1-2-3-4?". What does Lex use behind the scenes as…
Zach S
  • 21
  • 2
2
votes
1 answer

AWS Transcribe error on iOS: A server with the specified hostname could not be found

The code below generates this error with AWS Transcribe on iOS: Task <1B377509-91AE-43C0-8F24-F28FE7B583AC>.<1> load failed with error Error Domain=NSURLErrorDomain Code=-1003 "A server with the specified hostname could not be found."…
Crashalot
  • 33,605
  • 61
  • 269
  • 439
2
votes
1 answer

Access results of AWS Transcribe job with Java SDK

I have a AWS Transcribe job that gives me a URI when completed. This URI should be where the transcription text is stored. I want to access that text with the Java SDK, but GetObject does not seem to support this option. How do I access the text…
1
vote
0 answers

Encode MediaRecorder stream in PCM format for AWS transcribe

So I'm trying to use AWS transcribe medical but unable to achieve as AWS transcribe medical require "pcm" encoded audio data. I tried multiple custom function but no luck. I want to use something like MediaRecorder start method because i want to…
1
2
3
9 10