Spotlight textual content because it’s being spoken utilizing Amazon Polly

Amazon Polly is a service that turns textual content into lifelike speech. It allows the event of an entire class of functions that may convert textual content into speech in a number of languages.

This service can be utilized by chatbots, audio books, and different text-to-speech functions along side different AWS AI or machine studying (ML) providers. For instance, Amazon Lex and Amazon Polly could be mixed to create a chatbot that engages in a two-way dialog with a consumer and performs sure duties based mostly on the consumer’s instructions. Amazon Transcribe, Amazon Translate, and Amazon Polly could be mixed to transcribe speech to textual content within the supply language, translate it to a special language, and communicate it.

On this submit, we current an attention-grabbing strategy for highlighting textual content because it’s being spoken utilizing Amazon Polly. This answer can be utilized in lots of text-to-speech functions to do the next:

• Add visible capabilities to audio in books, web sites, and blogs
• Enhance comprehension when clients try to know the textual content quickly because it’s being spoken

Our answer provides the consumer (the browser, on this instance), the power to know what textual content (phrase or sentence) is being spoken by Amazon Polly at any immediate. This permits the consumer to dynamically spotlight the textual content because it’s being spoken. Such a functionality is beneficial for offering visible assist to speech for the use circumstances talked about beforehand.

Our answer could be prolonged to carry out further duties in addition to highlighting textual content. For instance, the browser can present photographs, play music, or carry out different animations on the entrance finish because the textual content is being spoken. This functionality is beneficial for creating dynamic audio books, instructional content material, and richer text-to-speech functions.

Resolution overview

At its core, the answer makes use of Amazon Polly to transform a string of textual content into speech. The textual content could be enter from the browser or by way of an API name to the endpoint uncovered by our answer. The speech generated by Amazon Polly is saved as an audio file (MP3 format) in an Amazon Simple Storage Service (Amazon S3) bucket.

Nonetheless, utilizing the audio file alone, the browser can’t discover what elements of the textual content are being spoken at any immediate as a result of we don’t have granular data on when every phrase is spoken.

Amazon Polly gives a technique to get hold of this utilizing speech marks. Speech marks are saved in a textual content file that exhibits the time (measured in milliseconds from begin of the audio) when every phrase or sentence is spoken.

Amazon Polly returns speech mark objects in a line-delimited JSON stream. A speech mark object comprises the next fields:

• Time – The timestamp in milliseconds from the start of the corresponding audio stream
• Sort – The kind of speech mark (sentence, phrase, viseme, or SSML)
• Begin – The offset in bytes (not characters) of the beginning of the thing within the enter textual content (not together with viseme marks)
• Finish – The offset in bytes (not characters) of the thing’s finish within the enter textual content (not together with viseme marks)
• Worth – This varies relying on the kind of speech mark:
  • SSML – <mark> SSML tag
  • Viseme – The viseme identify
  • Phrase or sentence – A substring of the enter textual content as delimited by the beginning and finish fields

For instance, the sentence “Mary had a bit of lamb” can provide the following speech marks file for those who use SpeechMarkTypes = [“word”, “sentence”] within the API name to acquire the speech marks:

{"time":0,"kind":"sentence","begin":0,"finish":23,"worth":"Mary had a bit of lamb."}
{"time":6,"kind":"phrase","begin":0,"finish":4,"worth":"Mary"}
{"time":373,"kind":"phrase","begin":5,"finish":8,"worth":"had"}
{"time":604,"kind":"phrase","begin":9,"finish":10,"worth":"a"}
{"time":643,"kind":"phrase","begin":11,"finish":17,"worth":"little"}
{"time":882,"kind":"phrase","begin":18, "finish":22,"worth":"lamb"}

The phrase “had” (on the finish of line 3) begins 373 milliseconds after the audio stream begins, begins at byte 5, and ends at byte 8 of the enter textual content.

Structure overview

The structure of our answer is introduced within the following diagram.

Spotlight Textual content because it’s spoken, utilizing Amazon Polly

Our web site for the answer is saved on Amazon S3 as static information (JavaScript, HTML), that are hosted in Amazon CloudFront (1) and served to the end-user’s browser (2).

When the consumer enters textual content within the browser by way of a easy HTML kind, it’s processed by JavaScript within the browser. This calls an API (3) by way of Amazon API Gateway, to invoke an AWS Lambda perform (4). The Lambda perform calls Amazon Polly (5) to generate speech (audio) and speech marks (JSON) information. Two calls are made to Amazon Polly to fetch the audio and speech marks information. The calls are made utilizing JavaScript async features. The output of those calls is the audio and speech marks information, that are saved in Amazon S3 (6a). To keep away from a number of customers overwriting every others’ information within the S3 bucket, the information are saved in a folder with a timestamp. This minimizes the possibilities of two customers overwriting every others’ information in Amazon S3. For a manufacturing launch, we are able to make use of extra strong approaches to segregate customers’ information based mostly on consumer ID or timestamp and different distinctive traits.

The Lambda perform creates pre-signed URLs for the speech and speech marks information and returns them to the browser within the type of an array (7, 8, 9).

When the browser sends the textual content file to the API endpoint (3), it will get again two pre-signed URLs for the audio file and the speech marks file in a single synchronous invocation (9). That is indicated by the important thing image subsequent to the arrow.

A JavaScript perform within the browser fetches the speech marks file and the audio from their URL handles (10). It units up the audio participant to play the audio. (The HTML audio tag is used for this objective).

When the consumer clicks the play button, it parses the speech marks retrieved within the earlier step to create a sequence of timed occasions utilizing timeouts. The occasions invoke a callback perform, which is one other JavaScript perform used to focus on the spoken textual content within the browser. Concurrently, the JavaScript perform streams the audio file from its URL deal with.

The result’s that the occasions are run on the applicable occasions to focus on the textual content because it’s spoken whereas the audio is being performed. Using JavaScript timeouts gives us the synchronization of the audio with the highlighted textual content.

Stipulations

To run this answer, you want an AWS account with an AWS Identity and Access Management (IAM) consumer who has permission to make use of Amazon CloudFront, Amazon API Gateway, Amazon Polly, Amazon S3, AWS Lambda, and AWS Step Capabilities.

Use Lambda to generate speech and speech marks

The next code invokes the Amazon Polly synthesize_speech perform two occasions to fetch the audio and speech marks file. They’re run as asynchronous features and coordinated to return the consequence on the similar time utilizing guarantees.

const p1 = new Promise(doSynthesizeSpeech marks);
const p2 = new Promise(doSynthesizeSpeech);
var consequence;

await Promise.all([p1, p2])
.then((values) => {
//return array of presigned urls 
     console.log('Values:', values);
     consequence = { "output" : values };
})
.catch((err) => {
     console.log("Error:" + err);
     consequence = err;
});

On the JavaScript facet, the textual content highlighting is completed by highlighter(begin, end, phrase) and the timed occasions are set by setTimers():

perform highlighter(begin, end, phrase) {
     let textarea = doc.getElementById("postText");
     //console.log(begin + "," + end + "," + phrase);
     textarea.focus();
     textarea.setSelectionRange(begin, end);
}

perform setTimers() {
     let speech marksStr = sessionStorage.getItem("speech marks");
     //learn by way of the speech marks file and set timers for each phrase
     console.log(speech marksStr);
     let speech marks = speech marksStr.cut up("n");
     for (let i = 0; i < speech marks.size; i++) {
          //console.log(i + ":" + speech marks[i]);
          if (speech marks[i].size == 0) {
               proceed;
     }

     smjson = JSON.parse(speech marks[i]);
     t = smjson["time"];
     s = smjson["start"];
     f = smjson["end"]; 
     phrase = smjson["value"];
     setTimeout(highlighter, t, s, f, phrase);
     }
}

Different approaches

As an alternative of the earlier strategy, you possibly can take into account a number of options:

• Create each the speech marks and audio information inside a Step Capabilities state machine. The state machine can invoke the parallel department situation to invoke two completely different Lambda features: one to generate speech and one other to generate speech marks. The code for this may be discovered within the using-step-functions subfolder within the Github repo.
• Invoke Amazon Polly asynchronously to generate the audio and speech marks. This strategy can be utilized if the textual content content material is giant or the consumer doesn’t want a real-time response. For extra particulars about creating lengthy audio information, confer with Creating Long Audio Files.
• Have Amazon Polly create the presigned URL straight utilizing the generate_presigned_url name on the Amazon Polly consumer in Boto3. For those who go along with this strategy, Amazon Polly generates the audio and speech marks newly each time. In our present strategy, we retailer these information in Amazon S3. Though these saved information aren’t accessible from the browser in our model of the code, you possibly can modify the code to play beforehand generated audio information by fetching them from Amazon S3 (as an alternative of regenerating the audio for the textual content once more utilizing Amazon Polly). We have now extra code examples for accessing Amazon Polly with Python within the AWS Code Library.

Create the answer

The whole answer is on the market from our Github repo. To create this answer in your account, comply with the directions within the README.md file. The answer contains an AWS CloudFormation template to provision your assets.

Cleanup

To scrub up the assets created on this demo, carry out the next steps:

1. Delete the S3 buckets created to retailer the CloudFormation template (Bucket A), the supply code (Bucket B) and the web site (pth-cf-text-highlighter-website-[Suffix]).
2. Delete the CloudFormation stack pth-cf.
3. Delete the S3 bucket containing the speech information (pth-speech-[Suffix]). This bucket was created by the CloudFormation template to retailer the audio and speech marks information generated by Amazon Polly.

Abstract

On this submit, we confirmed an instance of an answer that may spotlight textual content because it’s being spoken utilizing Amazon Polly. It was developed utilizing the Amazon Polly speech marks function, which gives us markers for the place every phrase or sentence begins in an audio file.

The answer is on the market as a CloudFormation template. It may be deployed as is to any net software that performs text-to-speech conversion. This is able to be helpful for including visible capabilities to audio in books, avatars with lip-sync capabilities (utilizing viseme speech marks), web sites, and blogs, and for aiding individuals with listening to impairments.

It may be prolonged to carry out further duties in addition to highlighting textual content. For instance, the browser can present photographs, play music, and carry out different animations on the entrance finish whereas the textual content is being spoken. This functionality could be helpful for creating dynamic audio books, instructional content material, and richer text-to-speech functions.

We welcome you to check out this answer and be taught extra in regards to the related AWS providers from the next hyperlinks. You possibly can lengthen the performance to your particular wants.

Concerning the Writer

Varad G Varadarajan is a Trusted Advisor and Area CTO for Digital Native Companies (DNB) clients at AWS. He helps them architect and construct modern options at scale utilizing AWS services and products. Varad’s areas of curiosity are IT technique consulting, structure, and product administration. Exterior of labor, Varad enjoys artistic writing, watching motion pictures with household and buddies, and touring.