How to Convert Speech to Text for FREE Using Whisper AI & Google Colab (Step-by-Step Tutorial)

In this video, I’ll show you how to use OpenAI’s Whisper AI to transcribe audio or video files with amazing accuracy, all for free and without any local downloads! I’ll walk you through the process step-by-step using Google Colab, which requires no coding experience.

Plus, I’ll share a common mistake I made while using Google Colab so you can avoid losing your transcription work. Whether you’re working with podcasts, interviews, or YouTube videos, this tutorial is designed to make transcription effortless.

Stay till the end to make sure you don’t miss out!

Here’s the timestamp summary for your convenience:

00:00 Intro: Turning audio into text for free
00:09 No Downloads: No local installation needed
00:17 Whisper AI & Colab: Using Whisper AI with Google Colab
00:50 Google Colab Setup: How to use Google Colab
01:58 Runtime Options: Choosing CPU vs GPU
03:37 Install Packages: Setting up Whisper and FFmpeg
04:25 Upload Files: Adding audio/video files to Colab
05:25 Choose Model: Picking the right Whisper model
06:16 Run Transcription: Executing transcription
07:07 File Outputs: Different file types explained
07:44 Avoid File Loss: Save files before Colab resets

Thank you for watching! Let me know if you have any questions down in the comment section! :-)

[ElleWang]

00:00 Intro: Turning audio into text for free
00:09 No Downloads: No local installation needed
00:17 Whisper AI & Colab: Using Whisper AI with Google Colab
00:50 Google Colab Setup: How to use Google Colab
01:58 Runtime Options: Choosing CPU vs GPU
03:37 Install Packages: Setting up Whisper and FFmpeg
04:25 Upload Files: Adding audio/video files to Colab
05:25 Choose Model: Picking the right Whisper model
06:16 Run Transcription: Executing transcription
07:07 File Outputs: Different file types explained
07:44 Avoid File Loss: Save files before Colab resets

Thank you for watching! Let me know if you have any questions down in the comment section! 😀

[htdstvm]

Amazing video. One of the best. Would love to see similar videos for non-technical professionals on AI models that they can use regularly. Do not know various use cases that AI models can help with, but this was a great discovery. Thanks!

[RamKumar-vbet]

A great video, thanks for sharing. A question - Do we need to install Whisper and Collobratory - every time we login, or they remain installed even after logging out? Thanks again!

[piqueselio]

Interesting video, well done and explained. Thanks, it was helpful to me.

[angelatdcas]

Thank you, Elle, but I got totally lost when you said to install packages directly from the source... where do I find these packages? I´m totally out of my comfort zone. I need to translate a video from English and Dutch into Spanish and do a voice-over to the video. So I thought to transcript the video and read it for the voice-over. Unless you know a faster or more efficient way... Could you possibly help me? Thank you again

[RisottosWife]

Thank you so much! I really appreciate it!

[htdstvm]

Thanks for sharing. A quick question - when I transcribe a file, it sometimes stops transcribing during the process showing it completed, when it has not. Is there a way (or a code) that resumes the transcribing process, where it last left off? At present, the only option is to start process again. Thanks!

[bennguyen]

Any suggestions for an offline / transcription approach? For example, I'd like to make a python application and run it on an old PC that wakes up on the voice command "Hey Ben".. then it would decode the command that follows (it'll be in the form "R193", "C2" etc). Any suggestions?


For example, I was thinking of using WebRTCVAD (or Silero-VAD) + Mycroft Precise Runner (now OpenVoiceOS) + RealtimeSTT? Or perhaps a single solution like Vosk?

If I did connect it to the internet.. how does pricing work? And with so many APIs, is there a single api/service that works with any of the online Speech-To-Text transcribers.. OpenAI/Grok (whisper), mistral, Google Cloud Speech-to-Text API, Amazon Transcribe, DeepSeek Speech-to-Text Translator, Claude, etc?

[cuk]

Hey, thank you so much for this video, So heplful

Just wondering
Do you know a method to convert foreign language speech video to english text please?

[FundacionUPIPADE]

Thank you so much for the tool! However I uploaded a large wav file -one hour lecture- and the text was incomplete, do you know what could have happened?

[formationWPfacile]

Thank you Elle. I found a Chinese drama on YouTube (mandarine speaking) and I would like to get the Chinese text to convert it in Pinyin to learn Chinese mandarin.
Do you think it's possible with this tool? The YouTube video has English captions and Chinese characters (transcription is only in English) but I need PinYin to learn how to prounounce each words. If I get the text of the video in Chinese, I know how to convert it into Pinyin with free websites. Watching dramas is a great way to study a language.

[MohammedKhan-qsnr]

it took me 4 mins to transcribe a 30 sec audio wav file, is that expected? also does this work with aac file, also thank you so much for sharing this

[waichow]

Hi, is there a way to get transcript from a youtube video that didn't have transcription in built. For example, they didn't activate CC caption. Thanks

[steffenb.]

Hi ElleWang, I have installed now Colab, but I do not find it afterwards in the selection. Where is the problem?

[yoyoschmo]

What about YouTube? I have the link or the video downloaded onto YOUTUBE but can’t get video to my computer

[Tom]

Can you also make a Google Collab on free talking avatar ? Thank you.

[ilham-zjm]

idk what is wrong with mine i cant do it i got 500 audios to transcript

[Tom]

Hi! Can you make a Google Collab on TTS for free ala eleven labs

[tarekolya]

I can’t find in google drive in my i pad

[existentialbaby]

i am running faster-whisper on my 2016 entry level potato laptop