Real-time Speech Recognition in 15 minutes with AssemblyAI

Рет қаралды 152,580

2 жыл бұрын

Get your free speech-to-text API token 👇
www.assemblyai.com/?...
Transcribing in real-time is a super skill only court reporters can brag about. But luckily, we don’t need to learn how to type fast to get transcriptions of audio quickly. Thanks to Assembly AI’s Streaming Speech-to-Text model (previously real-time speech recognition), it is very simple to set up a python script that can listen for audio and turn it to text.
In this video, we will see how to create this script on Python with the help of pyaudio, web sockets and asynchronous functions. The app will have the power to listen to audio input through a microphone and display the transcription in real-time. We will integrate this code into a simple Streamlit application to showcase the real-time speech recognition with a touch of interactivity.
If you’d like to follow along, don’t forget to get your own AssemblyAI API token for free at assemblyai.com
You can find the code from this tutorial in this GitHub repository: github.com/misraturp/Real-tim...
Find the written form of this tutorial here: www.assemblyai.com/blog/real-...
AssemblyAI Streaming STT docs: www.assemblyai.com/docs/speec...

Пікірлер: 72

@saifullahkhan9837 2 жыл бұрын

The accuracy and formatting is quite interesting here.

@AssemblyAI 2 жыл бұрын

Thank you! - Mısra

@debojitmandal8670 7 ай бұрын

@@AssemblyAIhi what if I want the input to be not from microphone and i want it from my speaker or laptop speaker how do I do it then.

@lfmtube Жыл бұрын

Most instructional and useful video. Thank you.

@AssemblyAI Жыл бұрын

You're very welcome!

3 ай бұрын

Thanks for everything :)

@otomakannioc8213 11 ай бұрын

Very sympathic and engaging presentation. Maybe the most beautiful side of Artificial Intelligence 😊

@AssemblyAI 11 ай бұрын

Thank you!

@amineelarif7001 2 жыл бұрын

that is sick! goodjob

@AssemblyAI 2 жыл бұрын

Thank you Amine! - Mısra

@slimyelow 9 ай бұрын

Very kewl it works. However for the live service a $8 minimum is required. - but totally worth it

@pjayo Жыл бұрын

Is there a JavaScript version of this video please? Both service side and front end…

@Pinkijhabnp 8 ай бұрын

Thank you for this nice tutorial

@AssemblyAI 8 ай бұрын

Glad you liked it

@ckames22 2 жыл бұрын

Awesome 👍

@AssemblyAI 2 жыл бұрын

Thank you!

@Asparuh.Emilov 2 жыл бұрын

This is really awesome! I would prefer though to see the final result as a short highlights at the beginning of your videos before you go into the details of how to. But thanks anyway for the effort and the time! Hugs!

@AssemblyAI 2 жыл бұрын

Thanks for the feedback! It's definitely a good idea to give an impression of the app that is being built. With the newer videos we do a preview at the beginning of the videos indeed. - Mısra

@Asparuh.Emilov 2 жыл бұрын

@@AssemblyAI 🤗🤗♥️♥️

@MrThought2012 11 ай бұрын

Very nice and easy setup! Took me ages to achieve the same with whisper. However, are you planning to support other languages, german, french or even a multilinugal model?

@omarsiddiqi5018 8 ай бұрын

Can I ask how you were able to do it?

@ashiqashervegar7973 Жыл бұрын

How can I use this for transcribing particular chrome tabs for online meetings? Can you help me with that?

@HomelessRafi Жыл бұрын

How can I introduce um, ahs, and other filler words in to the Realtime transcription? I see it is an option for uploading an audio file

@1992kshitizyadav Ай бұрын

As of now, only the English language is supported in the live transcription feature. when can we expect more language support ?

@adhikesavan9377 2 жыл бұрын

when i tried to install pyaudio terminal displays this error: "Cannot open include file: 'Python.h': No such file or directory "

@claudiotassis Жыл бұрын

Incredible video. Would I be able to use chatGPT, as an intermediate, to correct the sentences based on vocabulary and grammar, and after that, get the response from that chatGPT "reviewed" sentences?

@mohamedshagie3342 Жыл бұрын

Yup i tried to make it but it worked only text cant use speak 😅

@lookersky6145 Жыл бұрын

I've this installed and worked on windows. My question is that Real-time Speech Recognition only recognize english ? Does it support other languages ? Thank you.

@fahnub Жыл бұрын

Does it also offer diarization in real time?

@weebiesoftware6296 2 ай бұрын

I want to implement a realtime app using voice recognition on python 3 / android 11 on my samsung s22. It's my understanding portaudio is NOT supported on Android 11. Is portaudio your only way to get to the mic?

@spinal_cord Жыл бұрын

I know this is a little old, but I get a 4002 error, what might cause that?

@walker71391 11 ай бұрын

Did you ask ChatGPT?

@bakhshizade 8 ай бұрын

I am here for Freddie.

@PoojaVerma-sl6mg 9 ай бұрын

Could you please instruct me on how I can include this in my Angular project?

@usus8420 2 ай бұрын

hi great works but what about smartphone ?

@REALVIBESTV Жыл бұрын

Can this work in Unreal Engine 5

@Miguel-hq1lx 2 ай бұрын

is it possible to transcribe in real-time in other languages, such as spanish?

@KashyapJadav Жыл бұрын

Live transcript is paid version?

@moncefarajdal4582 2 жыл бұрын

Can you please let me know how can I integrate this in my JAVA Maven project?

@AssemblyAI 2 жыл бұрын

Hey Moncef, unfortunately I also don't have experience on that. -Mısra

@borr2749 Жыл бұрын

Assembly ai real time transcription doesn't have a free trial ?

@onintsoavola5698 6 ай бұрын

Is it possible to make it faster ? The transcription takes a little time

@user-mx5lv5qp5y 11 ай бұрын

can you pls let me know how to save that text

@loubino18 4 ай бұрын

Should have mentioned cost to go to pro version.... why hide it?

@IntricateMoon Жыл бұрын

I'm on windows, When I try to run it it does nothing, just creates a new line on the terminal. when I cloned the github repo, it was working, hmmm

@AssemblyAI Жыл бұрын

Have you tried speaking while the code is running? It might be that you don't have a microphone connected to the computer.

@eagold 2 жыл бұрын

buut.. if i have no money to buy the pro key?😕

@AssemblyAI 2 жыл бұрын

You can get started for free!

@rubibeats Жыл бұрын

how to add custom ui?

@MDMUHTADEEFAIAZKHANSOUMIK Жыл бұрын

Can we setup Bangla language for this system?

@GiulianoGolfieri Жыл бұрын

Is it possible to use this service in other languages apart from English?

@tiagofyhnesteves74 Жыл бұрын

im also trying to find an answer to this question

@GiulianoGolfieri Жыл бұрын

@@tiagofyhnesteves74 they answered to me privately. It's not possible yet. I switched to Azure cognitive services, which is multi-language.

@frizzfrizz3550 8 ай бұрын

@@GiulianoGolfieri I had taken it for granted that it was a multilingual service, a fucking morning's work wasted. Grazie della info, Giuliano

@parameswaranesnsce-cse9491 6 ай бұрын

can we speak any indic languages , will this endpoint will transcribe or not ?

@AssemblyAI 6 ай бұрын

Yes AssemblyAI's API supports Hindi Transcription, check out this tutorial: kzfaq.info/get/bejne/ab2cgbJ0yt_dmoU.html

@siamkamelia87 2 жыл бұрын

does this work for song transcription ? in real time ?

@AssemblyAI 2 жыл бұрын

Hey Siam, depending on the amount of background music and clarity of pronunciation you'd get varying levels of success with transcribing songs.

@angelfernando8954 2 жыл бұрын

Hi. how can i change the lenguage to transcript in spanish?

@AssemblyAI 2 жыл бұрын

Hey Angel, here is the documentation on transcribing in languages other than English. docs.assemblyai.com/walkthroughs#specifying-a-language

@dirtydevil81 2 жыл бұрын

@@AssemblyAI But do different languages work with realtime transcription on this specific endpoint? The documentation, regarding changing the language, is not clear about this.

@giovanniied Жыл бұрын

@@dirtydevil81 do you find a solution?