Send Audio For Transcription with Gladia API on Recording Completed (Instant) from Zoom API

Pipedream makes it easy to connect APIs for Gladia, Zoom and 2,200+ other apps remarkably fast.

Trigger workflow on

Recording Completed (Instant) from the Zoom API

Next, do this

Send Audio For Transcription with the Gladia API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a Zoom trigger and Gladia action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the Recording Completed (Instant) trigger
1. Connect your Zoom account
2. Optional- Select one or more Meeting Filter
3. Optional- Configure Include Audio Recordings
4. Optional- Configure Include Chat Transcripts
5. Configure apphook
Configure the Send Audio For Transcription action
1. Connect your Gladia account
2. Optional- Configure Audio
3. Optional- Configure Audio URL
4. Optional- Configure Toggle Noise Reduction
5. Optional- Configure Transcription Hint
6. Optional- Configure Toggle Diarization
7. Optional- Select a Target Translation Language
8. Optional- Configure Toggle Direct Translation
9. Optional- Select a Language Behaviour
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

Recording Completed (Instant) on Zoom

Description:Emit new event each time a new recording completes for a meeting or webinar where you're the host

Version:0.1.3

Key:zoom-recording-completed

View on GitHub

Zoom Overview#

The Zoom API lets you tap into a rich set of functionalities to enhance the video conferencing experience within your own app or workflow. With the Zoom API on Pipedream, you can automatically create meetings, manage users, send meeting notifications, and more, orchestrating these actions within a broader automation. This allows for seamless integration with other services, enabling both data collection and action triggers based on Zoom events.

Pipedream workflows allow you to run any Node.js code that connects to the Zoom API. Just create a new workflow, then add prebuilt Zoom actions (create a meeting, send a chat message, etc.) or write your own code. These workflows can be triggered by HTTP requests, timers, email, or on any app-based event (new tweets, a Github PR, Zoom events, etc).

Trigger Code#

import common from "../common/common.mjs";
import constants from "../common/constants.mjs";

export default {
  ...common,
  key: "zoom-recording-completed",
  name: "Recording Completed (Instant)",
  description: "Emit new event each time a new recording completes for a meeting or webinar where you're the host",
  version: "0.1.3",
  type: "source",
  dedupe: "unique",
  props: {
    ...common.props,
    meetingIds: {
      type: "integer[]",
      label: "Meeting Filter",
      description: "Optionally filter for events for one or more meetings",
      propDefinition: [
        common.props.app,
        "meetingId",
      ],
    },
    includeAudioRecordings: {
      propDefinition: [
        common.props.app,
        "includeAudioRecordings",
      ],
    },
    includeChatTranscripts: {
      propDefinition: [
        common.props.app,
        "includeChatTranscripts",
      ],
    },
    // eslint-disable-next-line pipedream/props-label, pipedream/props-description
    apphook: {
      type: "$.interface.apphook",
      appProp: "app",
      eventNames() {
        return [
          constants.CUSTOM_EVENT_TYPES.RECORDING_COMPLETED,
        ];
      },
    },
  },
  hooks: {
    async deploy() {
      const { meetings } = await this.app.listRecordings({
        params: {
          from: this.monthAgo(),
          to: new Date().toISOString()
            .slice(0, 10),
          page_size: 25,
        },
      });
      if (!meetings || meetings.length === 0) {
        return;
      }
      for (const meeting of meetings) {
        if (!this.isMeetingRelevant(meeting)) {
          continue;
        }
        for (const file of meeting.recording_files) {
          if (!this.isFileRelevant(file)) {
            continue;
          }
          this.emitEvent(file, meeting);
        }
      }
    },
  },
  methods: {
    ...common.methods,
    isMeetingRelevant(meeting) {
      const {
        id, recording_files,
      } = meeting;

      if (!recording_files || recording_files.length === 0) {
        console.log("No files in recording. Exiting");
        return false;
      }

      if (this.meetingIds && this.meetingIds.length > 0 && !this.meetingIds.includes(id)) {
        console.log("Meeting ID does not match the filter rules.");
        return false;
      }
      return true;
    },
    isFileRelevant(file) {
      return !((file.status !== "completed")
        || (file.file_type === "M4A" && !this.includeAudioRecordings)
        || (file.file_type === "CHAT" && !this.includeChatTranscripts));
    },
    emitEvent(file, meeting, downloadToken = null) {
      this.$emit(
        {
          download_url_with_token: `${file.download_url}?access_token=${downloadToken}`,
          download_token: downloadToken,
          ...file,
          meeting_id_long: meeting.id, // Long ID is necessary for certain API operations
          meeting_topic: meeting.topic,
          host_id: meeting.host_id,
          host_email: meeting.host_email,
        },
        {
          id: file.id,
          summary: `${meeting.topic} — ${file.file_type}`,
          ts: +new Date(file.recording_end),
        },
      );
    },
  },
  async run(event) {
    if (event.event !== constants.CUSTOM_EVENT_TYPES.RECORDING_COMPLETED) {
      console.log("Not a recording.completed event. Exiting");
      return;
    }
    const { payload } = event;
    const {
      object,
      download_token: downloadToken,
    } = payload;
    const { recording_files: recordingFiles } = object;

    if (!this.isMeetingRelevant(object)) {
      return;
    }

    for (const file of recordingFiles) {
      if (!this.isFileRelevant(file)) {
        continue;
      }

      this.emitEvent(file, object, downloadToken);
    }
  },
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
Zoom	`app`	`app`	This component uses the Zoom app.
Meeting Filter	`meetingIds`	`integer[]`	Select a value from the drop down menu.
Include Audio Recordings	`includeAudioRecordings`	`boolean`	This source emits video (MP4) recordings only by default. Set this prop to true to include audio recordings
Include Chat Transcripts	`includeChatTranscripts`	`boolean`	This source emits video (MP4) recordings only by default. Set this prop to `true` to include chat transcripts
	`apphook`	`$.interface.apphook`

Trigger Authentication#

Zoom uses OAuth authentication. When you connect your Zoom account, Pipedream will open a popup window where you can sign into Zoom and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Zoom API.

Pipedream requests the following authorization scopes when you connect your account:

About Zoom#

Zoom is the leader in modern enterprise video communications, with an easy, reliable cloud platform for video and audio conferencing, chat, and webinars.

Action#

Send Audio For Transcription on Gladia

Description:Sends audio to Gladia for transcription and optional translation. [See the documentation](https://docs.gladia.io/reference/pre-recorded)

Version:0.0.1

Key:gladia-send-audio-for-transcription

View on GitHub

Gladia Overview#

The Gladia API offers a suite of AI-powered capabilities, including image recognition, text analysis, and language processing. With its integration on Pipedream, you can build serverless workflows to automate tasks like content moderation, data enrichment, and real-time translations. Leverage Gladia's AI functions within Pipedream to create powerful, event-driven workflows that respond to various triggers such as webhooks, schedules, or app events.

Action Code#

import { ConfigurationError } from "@pipedream/platform";
import FormData from "form-data";
import fs from "fs";
import {
  camelToSnakeCase, checkTmp,
} from "../../common/utils.mjs";
import gladia from "../../gladia.app.mjs";

export default {
  key: "gladia-send-audio-for-transcription",
  name: "Send Audio For Transcription",
  description: "Sends audio to Gladia for transcription and optional translation. [See the documentation](https://docs.gladia.io/reference/pre-recorded)",
  version: "0.0.1",
  type: "action",
  props: {
    gladia,
    audio: {
      propDefinition: [
        gladia,
        "audio",
      ],
      optional: true,
    },
    audioUrl: {
      propDefinition: [
        gladia,
        "audioUrl",
      ],
      optional: true,
    },
    toggleNoiseReduction: {
      propDefinition: [
        gladia,
        "toggleNoiseReduction",
      ],
      optional: true,
    },
    transcriptionHint: {
      propDefinition: [
        gladia,
        "transcriptionHint",
      ],
      optional: true,
    },
    toggleDiarization: {
      propDefinition: [
        gladia,
        "toggleDiarization",
      ],
      optional: true,
    },
    targetTranslationLanguage: {
      propDefinition: [
        gladia,
        "targetTranslationLanguage",
      ],
      optional: true,
    },
    toggleDirectTranslate: {
      propDefinition: [
        gladia,
        "toggleDirectTranslate",
      ],
      optional: true,
    },
    languageBehaviour: {
      propDefinition: [
        gladia,
        "languageBehaviour",
      ],
      reloadProps: true,
      optional: true,
    },
  },
  async additionalProps() {
    const props = {};
    if (this.languageBehaviour === "manual") {
      props.language = {
        type: "string",
        label: "Language",
        description: "If language_behaviour is set to manual, define the language to use for the transcription",
      };
    }
    return props;
  },
  async run({ $ }) {
    if (!this.audio && !this.audioUrl) {
      throw new ConfigurationError("You must provite whether **Audio** or **Audio URL**.");
    }

    const {
      gladia,
      audio,
      toggleNoiseReduction,
      toggleDiarization,
      toggleDirectTranslate,
      ...data
    } = this;

    const formData = new FormData();
    if (audio) {
      const filePath = checkTmp(audio);
      formData.append("audio", fs.createReadStream(filePath));
    }
    formData.append("toggle_noise_reduction", `${toggleNoiseReduction}`);
    formData.append("toggle_diarization", `${toggleDiarization}`);
    formData.append("toggle_direct_translate", `${toggleDirectTranslate}`);

    for (const [
      key,
      value,
    ] of Object.entries(data)) {
      formData.append(`${camelToSnakeCase(key)}`, value);
    }
    const response = await gladia.sendAudioForTranscription({
      data: formData,
      headers: formData.getHeaders(),
    });

    $.export("$summary", "The audio was successfully transcripted!");
    return response;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Gladia	`gladia`	`app`	This component uses the Gladia app.
Audio	`audio`	`string`	The path of the audio file in /tmp folder to be transcribed. The audio file should be in WAV format. To upload a file to /tmp folder, please follow the doc here
Audio URL	`audioUrl`	`string`	The URL of the audio file to be transcribed. The audio file should be in WAV format.
Toggle Noise Reduction	`toggleNoiseReduction`	`boolean`	Activate the noise reduction to improve transcription quality
Transcription Hint	`transcriptionHint`	`string`	Provide a custom vocabulary to the model to improve accuracy of transcribing context specific words, technical terms, names, etc.
Toggle Diarization	`toggleDiarization`	`boolean`	Activate the diarization of the audio
Target Translation Language	`targetTranslationLanguage`	`string`	Select a value from the drop down menu:`afrikaansalbanianamharicarabicarmenianasturianazerbaijanibashkirbelarusianbengalibosnianbretonbulgarianburmesecatalancebuanochinesecroatianczechdanishdutchenglishestonianfinnishflemishfrenchwestern frisianfulahgaelicgaliciangandageorgiangermangreekgujaratihaitianhausahebrewhindihungarianicelandicigboilokoindonesianirishitalianjapanesejavanesekannadakazakhkoreanlaolatvianlingalalithuanianluxembourgishmacedonianmalagasymalaymalayalammarathimoldavianmoldovanmongoliannepalinorwegianoccitanoriyapanjabipashtopolishportuguesepushtoromanianrussianserbiansindhisinhalaslovaksloveniansomalispanishsundaneseswahiliswatiswedishtagalogtamilthaitswanaturkishukrainianurduuzbekvalencianvietnamesewelshwolofxhosayiddishyoruba`
Toggle Direct Translation	`toggleDirectTranslate`	`boolean`	A boolean value indicating whether to perform direct translation. Set to true to use direct translation and false to disable direct translation.
Language Behaviour	`languageBehaviour`	`string`	Select a value from the drop down menu:`manualautomatic single languageautomatic multiple languages`

Send Audio For Transcription with Gladia API on Recording Completed (Instant) from Zoom API

Pipedream makes it easy to connect APIs for Gladia, Zoom and 2,200+ other apps remarkably fast.

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

1-24of2,200+apps by most popular

1
-
24
of
2,200+
apps by most popular