Create Transcription with OpenAI (ChatGPT) API on New Task Added from Google Tasks API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Google Tasks and 2,700+ other apps remarkably fast.

Trigger workflow on

New Task Added from the Google Tasks API

Next, do this

Create Transcription with the OpenAI (ChatGPT) 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 Google Tasks trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Task Added trigger
1. Connect your Google Tasks account
2. Configure timer
3. Select a Task List
4. Configure alert
Configure the Create Transcription action
1. Connect your OpenAI (ChatGPT) account
2. Configure File Path or URL
3. Select a Model
4. Optional- Configure Include
5. Optional- Configure Language
6. Optional- Configure Prompt
7. Optional- Select a Response Format
8. Optional- Configure Temperature
9. Optional- Configure Timestamp Granularities
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#

New Task Added on Google Tasks

Description:Emit new event for each task added to Google Tasks. [See the documentation](https://developers.google.com/tasks/reference/rest/v1/tasks/list)

Version:0.0.2

Key:google_tasks-new-task-added

View on GitHub

Google Tasks Overview#

The Google Tasks API allows you to manage and manipulate a user's tasks and task lists on Google Tasks directly from Pipedream. With this API, you can create, read, update, and delete tasks, as well as manage the lists themselves. This opens up possibilities for automating task management, syncing tasks with other systems, and creating custom task-based workflows that can increase productivity and ensure nothing falls through the cracks.

Trigger Code#

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

export default {
  ...common,
  key: "google_tasks-new-task-added",
  name: "New Task Added",
  description: "Emit new event for each task added to Google Tasks. [See the documentation](https://developers.google.com/tasks/reference/rest/v1/tasks/list)",
  version: "0.0.2",
  dedupe: "unique",
  type: "source",
  props: {
    ...common.props,
    taskListId: {
      propDefinition: [
        common.props.googleTasks,
        "taskListId",
      ],
    },
    alert: {
      propDefinition: [
        common.props.googleTasks,
        "alert",
      ],
    },
  },
  methods: {
    ...common.methods,
    emitEvents(tasks) {
      const sortedTasks = tasks.sort((t1, t2) => (new Date(t1.updated) - new Date(t2.updated)));
      for (const task of sortedTasks) {
        this.$emit(task, this.generateMeta(task));
      }
    },
    generateMeta(event) {
      return {
        id: event.id,
        summary: `New task: ${event.title}`,
        ts: new Date(event.updated),
      };
    },
    getParams() {
      return {
        maxResults: this._maxQueryResults(),
        updatedMin: this._getLastUpdate(),
      };
    },
  },
  async run() {
    const tasks = await this.googleTasks.paginate(
      this.googleTasks.getTasks.bind(this),
      this.getParams(),
      this.taskListId,
    );
    const maxDate = new Date(Math.max(...tasks.map((task) => new Date(task.updated))));
    this._setLastUpdate(maxDate);
    this.emitEvents(tasks);
  },
};

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
Google Tasks	`googleTasks`	`app`	This component uses the Google Tasks app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`
Task List	`taskListId`	`string`	Select a value from the drop down menu.

Trigger Authentication#

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

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

https://www.googleapis.com/auth/tasks

About Google Tasks#

Use Google Tasks to keep track of important to-dos that sync across all your devices.

Action#

Create Transcription on OpenAI (ChatGPT)

Description:Transcribes audio into the input language. [See the documentation](https://platform.openai.com/docs/api-reference/audio/createTranscription)

Version:0.3.0

Key:openai-create-transcription

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

import { getFileStreamAndMetadata } from "@pipedream/platform";
import openai from "../../openai.app.mjs";
import FormData from "form-data";

export default {
  key: "openai-create-transcription",
  name: "Create Transcription",
  description: "Transcribes audio into the input language. [See the documentation](https://platform.openai.com/docs/api-reference/audio/createTranscription)",
  version: "0.3.0",
  type: "action",
  props: {
    openai,
    file: {
      propDefinition: [
        openai,
        "file",
      ],
    },
    model: {
      type: "string",
      label: "Model",
      description: "ID of the model to use",
      options: [
        "gpt-4o-transcribe",
        "gpt-4o-mini-transcribe",
        "whisper-1",
      ],
    },
    include: {
      type: "string[]",
      label: "Include",
      description: "Additional information to include in the transcription response. `logprobs` will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. `logprobs` only works with response_format set to `json` and only with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`.",
      optional: true,
    },
    language: {
      type: "string",
      label: "Language",
      description: "The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. en) format will improve accuracy and latency.",
      default: "en",
      optional: true,
    },
    prompt: {
      type: "string",
      label: "Prompt",
      description: "An optional text to guide the model's style or continue a previous audio segment. The [prompt](https://platform.openai.com/docs/guides/speech-to-text#prompting) should match the audio language.",
      optional: true,
    },
    response_format: {
      type: "string",
      label: "Response Format",
      description: "The format of the output. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`.",
      options: [
        "json",
        "text",
        "srt",
        "verbose_json",
        "vtt",
      ],
      optional: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.",
      optional: true,
    },
    timestamp_granularities: {
      type: "string[]",
      label: "Timestamp Granularities",
      description: "The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.",
      optional: true,
    },
  },
  methods: {
    createTranscription(opts = {}) {
      return this.openai._makeRequest({
        method: "POST",
        path: "/audio/transcriptions",
        ...opts,
      });
    },
  },
  async run({ $ }) {
    const {
      /* eslint-disable no-unused-vars */
      openai,
      file,
      createTranscription,
      ...fields
    } = this;

    const data = new FormData();
    const {
      stream, metadata,
    } = await getFileStreamAndMetadata(file);

    data.append("file", stream, {
      contentType: metadata.contentType,
      knownLength: metadata.size,
      filename: metadata.name,
    });

    for (const [
      key,
      value,
    ] of Object.entries(fields)) {
      const v = Array.isArray(value)
        ? value.join(",")
        : value;
      data.append(key, v);
    }

    const response = await createTranscription({
      $,
      data,
      headers: data.getHeaders(),
    });

    $.export("$summary", "Successfully converted speech to text");
    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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
File Path or URL	`file`	`string`	The file to process. Provide either a file URL or a path to a file in the `/tmp` directory (for example, `/tmp/myFile.txt`). See the Assistants Tools guide to learn more about the types of files supported. The Fine-tuning API only supports `.jsonl` files.
Model	`model`	`string`	Select a value from the drop down menu:`gpt-4o-transcribegpt-4o-mini-transcribewhisper-1`
Include	`include`	`string[]`	Additional information to include in the transcription response. `logprobs` will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. `logprobs` only works with response_format set to `json` and only with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`.
Language	`language`	`string`	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.
Prompt	`prompt`	`string`	An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
Response Format	`response_format`	`string`	Select a value from the drop down menu:`jsontextsrtverbose_jsonvtt`
Temperature	`temperature`	`string`	The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
Timestamp Granularities	`timestamp_granularities`	`string[]`	The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Create Transcription with OpenAI (ChatGPT) API on New Task Added from Google Tasks API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), Google Tasks and 2,700+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,700+apps by most popular

1
-
24
of
2,700+
apps by most popular