Make Music With AI Vocals. Epic synthetic singing and rapping vocals for creative agencies, musicians, and coders.
Generates lyrics using a specified voice model. See the documentation
Delay the execution of your workflow for a specific amount of time (does not count against your compute time).
Get voice samples for a specific voice model. See the documentation
The Uberduck API offers text-to-speech capabilities with a variety of voice choices, from standard voices to celebrity impersonations. It enables you to convert text into lifelike speech, providing an API that can be used for creating audio content, voiceovers for videos, or for making interactive voice response systems more engaging. On Pipedream, you can build workflows that leverage this functionality, triggering voice synthesis with events from various sources and integrating with other apps for a seamless automation experience.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
uberduck: {
type: "app",
app: "uberduck",
}
},
async run({steps, $}) {
return await axios($, {
url: `https://api.uberduck.ai/voices`,
auth: {
username: `${this.uberduck.$auth.api_key}`,
password: `${this.uberduck.$auth.secret_key}`,
},
})
},
})
The Delay API in Pipedream is a built-in function that allows you to pause a workflow for a specified amount of time. This can be incredibly useful when you need to stagger API calls to avoid rate limits, wait for an external process to complete, or simply introduce a delay between actions in a sequence. With precision up to milliseconds, the Delay API provides a simple yet powerful tool for managing timing in automation workflows.
export default defineComponent({
async run({steps, $}) {
// Specify the amount of time to delay your workflow in milliseconds
return $.flow.delay(5000)
},
})