Deploy high-quality, natural-sounding human voices in dozens of languages.
The Amazon Polly API lets you convert text into lifelike speech using deep learning. With Polly, you can create applications that talk and build entirely new categories of speech-enabled products. Pipedream's platform enables you to integrate Polly's capabilities into workflows that can automate tasks, like generating audio files from blog posts or alert messages, and piping them to various services or storage solutions.
import AWS from 'aws-sdk'
import { PollyClient, StartSpeechSynthesisTaskCommand } from "@aws-sdk/client-polly"
export default defineComponent({
props: {
amazon_polly: {
type: "app",
app: "amazon_polly",
}
},
async run({steps, $}) {
const { accessKeyId, secretAccessKey } = auths.amazon_polly
// Create an Amazon Polly service client object.
const creds = new AWS.Credentials(accessKeyId, secretAccessKey);
const pollyClient = new PollyClient({ credentials: creds, region: "us-east-1" });
// Create input data
var data = {
OutputFormat: "mp3",
OutputS3BucketName: "videoanalyzerbucket",
Text: "Hello David, How are you?",
TextType: "text",
VoiceId: "Joanna",
SampleRate: "22050",
};
return await pollyClient.send(new StartSpeechSynthesisTaskCommand(data));
},
})
The Schedule app in Pipedream is a powerful tool that allows you to trigger workflows at regular intervals, ranging from every minute to once a year. This enables the automation of repetitive tasks and the scheduling of actions to occur without manual intervention. By leveraging this API, you can execute code, run integrations, and process data on a reliable schedule, all within Pipedream's serverless environment.