npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

@directus-labs/ai-transcription-operation

v1.1.0

Published

Use Deepgram's Speech Recognition API to generate transcripts from audio files.

Downloads

27

Readme

AI Transcription Operation

Generate transcripts from audio files within Directus Flows with this custom operation, powered by Deepgram.

The AI Transcription operation, showing a Deepgram API Key field and a File URL field.

This operation contains the following configuration options:

Required

Optional

  • Callback URL - process the transcript asynchronously by providing a callback URL. The Deepgram API will make a POST request to this url once transcription is completed.
  • Diarization - include speaker changes in the transcript.
  • Keywords - Uncommon proper nouns or other words to transcribe that are not a part of the model’s vocabulary. These follow this format keyword:intensifer.

If a Callback URL is NOT provided, the operation returns a JSON object containing the transcript, a breakdown of each word and timestamp, a paragraph-formatted transcript, and a breakdown of each paragraph and timestamp.

The output showing a JSON object containing a transcript and words.

You can use the operation to then save the result to a file description or item, or run further automation on the output.


If a Callback URL is provided, the operation does not wait for the transcript to finish generation. It immediately returns a JSON object containing the request_id provided by the Deepgram API and a message confirming successful submission.

The output showing a JSON object containing a confirmation message and request_id.

The request_id should be stored and used to identify the incoming transcript from Deepgram.

Once the transcript has been generated, the Deepgram API will make a POST request to the Callback URL you have provided. The request_id will be included in the metadata of that request.

Make sure that your Callback URL is configured to accept and handle the response from Deepgram's API. This could be another Directus Flow with an incoming Webhook Trigger or some other system.

Output

If no Callback URL is provided, the operation outputs a JSON object with the following structure:

{
    "confidence": 0.9995117,
    "transcript": "Hi. This is a long string with the full transcript. Complete with punctuation and capitalization."
    "words": [
        {
            "confidence": 0.9995117,
            "word": "word",
            "punctuated_word": "Hi.",
            "start": 0.08,
            "end": 0.3999998,
        }
    ],
    "paragraphs": {
        "transcript": "Hi.\n\nThis is a long string with the full transcript.\n\nComplete with punctuation and capitalization.",
        "paragraphs": [
            {
                "sentences": [
                    {
                        "start": 0.08,
                        "end": 0.3999998,
                        "text": "Hi."
                    }
                ],
                "num_words": 14,
                "start": 0.08,
                "end": 0.7075
            }
        ]
    }
}

If a Callback URL is provided, the operation outputs a JSON object with the following structure:

{
  "request_id": "42fc4c2b-09b3-4f5f-af04-3d1c9e9dc185",
  "message": "Transcription request submitted for processing."
}

Flow Setup

Automatically Transcribe New Files

Create a Flow with an Event Hook action trigger and a scope of files.upload. Use the AI Transciption operation, setting the File URL to https://your-directus-project-url/assets/{{ $trigger.key }}, being sure to provide your specific Directus Project URL.

This will work if your file is public, but if it isn't, you can append ?access_token=token to the File URL, replacing the value with a valid user token that has access to the file.

This operation will trigger on every new file upload, regardless of location or filetype. You may wish to add a conditional step between the trigger and transcription operation. The following condition rule will check that the file is audio:

{
    "$trigger": {
        "payload": {
            "type": {
                "_contains": "audio"
            }
        }
    }
}

Transcribe On-Demand

Create a Flow with a Manual trigger and select a collection with a file field, which should contain an audio file. Set the Location to Item Page Only. To receive the file ID create a Read Data operation for the same collection, setting IDs to {{ $trigger.body.keys[0] }}.

Use the AI Transciption operation, setting the File URL to https://your-directus-project-url/assets/{{ $last.file_field_name }}, being sure to provide your specific Directus Project URL and file field name.