Upload Media with Sonix API on New Fine Tuning Job Created from OpenAI (ChatGPT) API

Pipedream makes it easy to connect APIs for Sonix, OpenAI (ChatGPT) and 2,400+ other apps remarkably fast.

Trigger workflow on

New Fine Tuning Job Created from the OpenAI (ChatGPT) API

Next, do this

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

Select this integration
Configure the New Fine Tuning Job Created trigger
1. Connect your OpenAI (ChatGPT) account
2. Configure timer
Configure the Upload Media action
1. Connect your Sonix account
2. Optional- Configure File
3. Optional- Configure File URL
4. Select a Language
5. Optional- Select a Folder ID
6. Optional- Configure Name
7. Optional- Configure Transcript Text
8. Optional- Configure Keywords
9. Optional- Configure Custom Data
10. Optional- Configure Callback URL
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 Fine Tuning Job Created on OpenAI (ChatGPT)

Description:Emit new event when a new fine-tuning job is created in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/fine-tuning/list)

Version:0.0.10

Key:openai-new-fine-tuning-job-created

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:

Trigger Code#

import common from "../common/common.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  ...common,
  key: "openai-new-fine-tuning-job-created",
  name: "New Fine Tuning Job Created",
  description: "Emit new event when a new fine-tuning job is created in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/fine-tuning/list)",
  version: "0.0.10",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getData() {
      return this.openai.listFineTuningJobs();
    },
    getMeta(item) {
      return {
        id: item.id,
        summary: `New Fine Tuning Job: ${item.id}`,
        ts: item.created_at * 1000,
      };
    },
  },
  sampleEmit,
};

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
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

OpenAI (ChatGPT) uses API keys for authentication. When you connect your OpenAI (ChatGPT) account, Pipedream securely stores the keys so you can easily authenticate to OpenAI (ChatGPT) APIs in both code and no-code steps.

About OpenAI (ChatGPT)#

OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular models like ChatGPT, DALL-E, and Whisper.

Action#

Upload Media on Sonix

Description:Submits new media for processing. [See the documentation](https://sonix.ai/docs/api#new_media)

Version:0.0.1

Key:sonix-upload-media

View on GitHub

Sonix Overview#

The Sonix API enables automated transcription of audio and video files into text, offering functions like uploading media, managing files, and retrieving transcripts. Leveraging Pipedream’s capabilities, you can integrate the Sonix API with various services to streamline media processing workflows, making transcription tasks more efficient. By automating interactions with Sonix, you can trigger actions based on the transcription status, analyze content, and connect transcribed text with other apps for further processing or analysis.

Action Code#

import { ConfigurationError } from "@pipedream/platform";
import FormData from "form-data";
import fs from "fs";
import { LANGUAGE_OPTIONS } from "../../common/constants.mjs";
import { checkTmp } from "../../common/utils.mjs";
import sonix from "../../sonix.app.mjs";

export default {
  key: "sonix-upload-media",
  name: "Upload Media",
  description: "Submits new media for processing. [See the documentation](https://sonix.ai/docs/api#new_media)",
  version: "0.0.1",
  type: "action",
  props: {
    sonix,
    file: {
      type: "string",
      label: "File",
      description: "Path of the audio or video file in /tmp folder. The limit is 100MB using this parameter. For larger files, use **File URL**. `NOTE: Only one of **File** or **File URL** is required.` To upload a file to /tmp folder, please follow the [doc here](https://pipedream.com/docs/code/nodejs/working-with-files/#writing-a-file-to-tmp)",
      optional: true,
    },
    fileUrl: {
      type: "string",
      label: "File URL",
      description: "URL pointing to the audio/video file. `NOTE: Only one of **File** or **File URL** is required.`",
      optional: true,
    },
    language: {
      type: "string",
      label: "Language",
      description: "Language code for the transcription.",
      options: LANGUAGE_OPTIONS,
    },
    folderId: {
      propDefinition: [
        sonix,
        "folderId",
      ],
      optional: true,
    },
    name: {
      type: "string",
      label: "Name",
      description: "Name of the file in Sonix. If no name is provided, we will default to the filename.",
      optional: true,
    },
    transcriptText: {
      type: "boolean",
      label: "Transcript Text",
      description: "Existing transcript - if present, will align the transcript rather than transcribing.",
      optional: true,
    },
    keywords: {
      type: "string[]",
      label: "Keywords",
      description: "Comma separated list of words or phrases to use as hints to the transcription engine. If this is provided, then the account level keywords will not be used.",
      optional: true,
    },
    customData: {
      type: "object",
      label: "Custom Data",
      description: "Set of key-value pairs that you can attach to the media. This can be useful for storing additional information about file.",
      optional: true,
    },
    callbackUrl: {
      type: "string",
      label: "Callback URL",
      description: "URL for Sonix to make a POST request notifying of a change in transcript status (either failed or completed). The POST will include the media status JSON.",
      optional: true,
    },
  },
  async run({ $ }) {
    if (!this.file && !this.fileUrl) {
      throw new ConfigurationError("You must provite whether **File** or **File URL**.");
    }

    const formData = new FormData();

    if (this.file) {
      const filePath = checkTmp(this.file);
      formData.append("file", fs.createReadStream(filePath));
    }

    this.fileUrl && formData.append("file_url", this.fileUrl);
    this.language && formData.append("language", this.language);
    this.name && formData.append("name", this.name);
    this.transcriptText && formData.append("transcript_text", `${this.transcriptText}`);
    this.folderId && formData.append("folder_id", this.folderId);
    this.keywords && formData.append("keywords", this.keywords.toString());
    this.customData && formData.append("custom_data", JSON.stringify(this.customData));
    this.callbackUrl && formData.append("callback_url", this.callbackUrl);

    const response = await this.sonix.submitNewMedia({
      data: formData,
      headers: formData.getHeaders(),
    });
    $.export("$summary", `Successfully uploaded media with ID: ${response.id}`);
    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
Sonix	`sonix`	`app`	This component uses the Sonix app.
File	`file`	`string`	Path of the audio or video file in /tmp folder. The limit is 100MB using this parameter. For larger files, use File URL. `NOTE: Only one of File or File URL is required.` To upload a file to /tmp folder, please follow the doc here
File URL	`fileUrl`	`string`	URL pointing to the audio/video file. `NOTE: Only one of File or File URL is required.`
Language	`language`	`string`	Select a value from the drop down menu:`{ "label": "English", "value": "en" }{ "label": "French", "value": "fr" }{ "label": "German", "value": "de" }{ "label": "Spanish", "value": "es" }{ "label": "Arabic", "value": "ar" }{ "label": "Armenian", "value": "hy-AM" }{ "label": "Bulgarian", "value": "bg" }{ "label": "Catalan", "value": "ca" }{ "label": "Croatian", "value": "hr" }{ "label": "Chinese (Cantonese)", "value": "yue-Hant-HK" }{ "label": "Chinese (Mandarin)", "value": "cmn-Hans-CN" }{ "label": "Czech", "value": "cs" }{ "label": "Danish", "value": "da" }{ "label": "Dutch", "value": "nl" }{ "label": "Finnish", "value": "fi" }{ "label": "Greek", "value": "el" }{ "label": "Hebrew", "value": "he-IL" }{ "label": "Hindi", "value": "hi" }{ "label": "Hungarian", "value": "hu" }{ "label": "Indonesian", "value": "id-ID" }{ "label": "Italian", "value": "it" }{ "label": "Japanese", "value": "ja" }{ "label": "Korean", "value": "ko" }{ "label": "Latvian", "value": "lv" }{ "label": "Lithuanian", "value": "lt" }{ "label": "Malay", "value": "ms-MY" }{ "label": "Norwegian", "value": "nb-NO" }{ "label": "Polish", "value": "pl" }{ "label": "Portuguese", "value": "pt" }{ "label": "Romanian", "value": "ro" }{ "label": "Russian", "value": "ru" }{ "label": "Slovak", "value": "sk" }{ "label": "Slovenian", "value": "sl" }{ "label": "Swedish", "value": "sv" }{ "label": "Thai", "value": "th-TH" }{ "label": "Turkish", "value": "tr-TR" }{ "label": "Ukrainian", "value": "uk" }{ "label": "Vietnamese", "value": "vi-VN" }`
Folder ID	`folderId`	`string`	Select a value from the drop down menu.
Name	`name`	`string`	Name of the file in Sonix. If no name is provided, we will default to the filename.
Transcript Text	`transcriptText`	`boolean`	Existing transcript - if present, will align the transcript rather than transcribing.
Keywords	`keywords`	`string[]`	Comma separated list of words or phrases to use as hints to the transcription engine. If this is provided, then the account level keywords will not be used.
Custom Data	`customData`	`object`	Set of key-value pairs that you can attach to the media. This can be useful for storing additional information about file.
Callback URL	`callbackUrl`	`string`	URL for Sonix to make a POST request notifying of a change in transcript status (either failed or completed). The POST will include the media status JSON.

Upload Media with Sonix API on New Fine Tuning Job Created from OpenAI (ChatGPT) API

Pipedream makes it easy to connect APIs for Sonix, OpenAI (ChatGPT) and 2,400+ other apps remarkably fast.

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

Developers ♥ Pipedream

1-24of2,400+apps by most popular

1
-
24
of
2,400+
apps by most popular