Access powerful AI models to transcribe and understand speech via a simple API.
Emit new event when a transcribed audio file from AssemblyAI is ready. See the documentation
Trigger your workflow on one or more days each month at a specific time (with timezone support).
Trigger your workflow on one or more days each week at a specific time (with timezone support).
Export your completed transcripts in SRT (srt) or VTT (vtt) format, which can be used for subtitles and closed captions in videos. See the documentation
Fetches a specific transcribed result from the AssemblyAI API. See the documentation
The AssemblyAI API provides powerful speech recognition and natural language processing capabilities. It allows users to transcribe audio, analyze sentiment, detect topics, and more. In Pipedream, you can leverage these features to create automated workflows that process audio and text data. Connect AssemblyAI to various apps and services, trigger actions based on the API's output, and build robust, serverless data pipelines.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
assemblyai: {
type: "app",
app: "assemblyai",
}
},
async run({steps, $}) {
const data = {
"audio_url": `{{your_audio_url}}`,
//for testing, try: https://storage.googleapis.com/aai-web-samples/espn-bears.m4a
}
return await axios($, {
method: "POST",
url: `https://api.assemblyai.com/v2/transcript`,
headers: {
"authorization": `${this.assemblyai.$auth.api_key}`,
},
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.