Deploy OpenAI's Whisper on Cloudflare Workers.AI
Learn to deploy OpenAI's Whisper via Cloudflare Workers.AI. Follow step-by-step instructions to transcribe audio files using the Whisper API.
File
Run OpenAIs Whisper on Cloudflare for Free using Workers AI [Speech to Text]
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: In this video, I will show you how to run OpenAI's Whisper on Cloudflare using Workers.AI. Before we begin, make sure you hit subscribe and tap the bell icon to get daily tech videos. Workers.AI is a new beta feature of Cloudflare that allows you to run popular AI models as workers. You can access them over the REST API and process the data. It supports OpenAI's Whisper as well and in this video I will show you how to do that and access it over API. Let's get started. Log into your Cloudflare account and then go to the AI section and launch Workers.AI. Here you will now see the list of models that it supports. OpenAI's Whisper is listed here as well. Now let's just deploy it. Open the model templates and then find speech to text. Give your worker a name and then scroll down to deploy it. It will take a few seconds and when it's done you will see the URL of the deployed worker. Now go to the website dashboard and then copy your account ID and save it somewhere. Next, you now need to generate an API token. For that, go to the Get Your API Token section. Click Create Token and then choose the Workers.AI template. Leave everything else here as default and click Continue to Summary. Copy the generated API token and then save it somewhere as well. Go to the folder where you have the audio file you want to transcribe. Use Shift and right-click on this folder and then select Open in Terminal option. Now you need to build the API call URL. We will use curl here but you can use some other programming languages such as Python and JavaScript. Replace account ID and API token that we copied earlier in this curl command. You can copy it from the description of this video. Enter the name of the audio file at the end of the curl command like this. Finally, copy-paste this entire command in the terminal. Hit Enter and wait for a few seconds. You will now get the final transcribed text. Copy it and then use it anywhere you like. You can now use the Whisper API on CloudLayer like with this AnyAudio file. This is it. This way, you can now easily deploy OpenAI's Whisper model on CloudLayer for free. If you found this video helpful, then check out more tech videos on our channel. Thanks for watching.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript