Speech To Text using ESP32
Вставка
- Опубліковано 4 жов 2024
- This video will guide you with how to convert any speech to text which you can further use for any of your projects.
This step is very useful for our upcoming project which is making our own voice assistant based on ChatGPT. Stay Tuned.....
To try out free trial version of Altium, click here - www.altium.com...
Get the best quality components from Octopart:
octopart.com/
⚡️⚡️ Order all components required for making this project using this single link - techiesms.com/...
You can support me🙏🏻 and also get benefitted on Patreon :- / techiesms
__________________________________________________________
👨🏻💻 Important Links 👨🏻💻
ESP32 ChatGPT Series Playlist - • Running ChatGPT on ESP...
Google Cloud URL - cloud.google.c...
Code used in this video - github.com/tec...
__________________________________________________________
Buy the components for your projects and support techiesms💡🔌
⚡️⚡️ Order all components required for making this project using this single link - techiesms.com/...
Or if you want to order only specific components then here is the list and link,
ESP32 Dev board - www.techiesms....
INMP441 Microphone -www.techiesms....
and many more such components are available at www.techiesms.com
__________________________________________________________
⏱ Time Stamps ⏱
__________________________________________________________
🎥 🎙 My Video Gear 🎙🎥
Camera - Canon 750d
Lens - 50mm f/1.8 STM Lens (amzn.to/32gqnsi), 24mm f/2.6
Key Light - Godox SL60W (amzn.to/3522mHe)
Fill Light/Back Light - Osaka Lightning Setup (amzn.to/2I5cdDi)
Tripod - amzn.to/3uNhC4H
Microphone - Zoom H1N(amzn.to/3Osh12A)
Editing - Final Cut Pro X on MacBook Pro ( amzn.to/3vHcSyJ )
__________________________________________________________
Get connected with techiesms everywhere..
Subscribe Main Channel :- bit.ly/techiesm...
Subscribe Shorts Channel :- bit.ly/techies...
Facebook :- / techiesms
Twitter :- / imtechiesms
Instagram :- / techiesms
Website :- www.techiesms.com
Telegram - @techiesms
__________________________________________________________
techiesms
explore | learn | share
In order to transcribe long form of Audio more than 1 minute. We need to use Speech-to-Text API and asynchronous speech recognition. In order to use that we need to enable the Google Cloud Storage Bucket. In this storage bucket, we need to store the long form of Audio digitally in the bucket and process those digital audio in the same way what you are doing for 2-3 second Audio . Excited to see the final outcome.
I have to slow video down to 75%. I didn't have enough caffeine to keep up. Thanks for these great videos.
At the start you say this is a stand alone? It's not it is dependent on the cloud service 😢
I really enjoy your videos in the way you present various information, thank you. I am a faithful follower
I'm asking why the newest version of Esp32 library shouldn't work
I have issue that is in output where in json data i get only totalbilltime and request id but i won't get the words what i spoke
Please help me with my issue
did you solve this problem? i have the same issue
Did you fix it
@@karthikn1126 Same here, What should we do?
Me too? Any solution?
@@manfredmichael_3ia097 Yes, Change the L/R Cable and connect it to the VDD instead :)
Hi Sir, Can i use 1 NodeMCU for microphone, and Other ESP32 Wrooms board for Chatgpt etc?
what if in Arduino IDE ESP32 latest version didn't work , there is no old versions of esp32 available to install
agree, same doubt
Does the google cloud cut money from later on??
off topic, I want to control a 12V DC LED using ESP 32 and Google Assistant, what are my options ?
why do I keep getting PK - The pubkey tag or value is invalid (only RSA and EC are supported) while trying to connect ?
Hi, may I know if it is possible to send the captured voices/sentences to any IoT Platform?
It shows the error nested too deeply is there any solution for it ?
G'day I am wondering if it can do Speech to Text, and how small can it really get? I saw the XIAO Esp32 being tiny.
I have a project that requires wireless, real-time Speech to Text capabilities, and 4 programmable buttons on it... in the smallest form factor possible... Max one index finger size.
Do you reckon it can be done with Esp32's or am I better off looking somewhere else?
what would you suggest?
HOW ABOUT STT VIA WEB PAGE. SO YOU CONVERT SPEECH FROM A WEBPAGE HOSTED IN ESP32.
GOOGLE API CAN BE DONE ON WEBPAGE AS WELL SO THAT SPEECH TIME IS NOT LIMITED
Oh this is Crazy, Speech to Text is really hard, especially if you make it Stand alone (aka no internet). Altium has amazing Free Videos, taught me how Electricity really flows, thanks Rick Hartley.
I'm glad you have a sponsor, sorry can't fork out 1/5 of my annual income for 1 the software
hi, is there a way not to press the RS button to restart the voice? I want to be like "Ok, google" and the ESP32 will listen and convert it to text
Did you do it ?
Hey Sachin, how can i increase the time of record into 5 second?
the connection failed, how can I fix it ?
Me too, did you fix it?
Are you fixed it ???@@Hybroid
@@AhmadSaadeh-fh4ko did u fix it?
did u find a solution for this ?
❤the king of home automation love you
I’m waiting for it, thank you
You're welcome 😊
hello sachin! I have problem about JSON API, my code don't answer this, do you have solved?
Please let me know your problem with a bit detail
@@techiesms My problem is that the Speech to Text JSON file is not read or the Speech to Text output does not work. So when I tried to speak, there was no answer. What do you think?
i have a same problem? Do you fix it? tks@@fitraanantioramadhani8695
@@fitraanantioramadhani8695 same problem what should I do ?
@@statusguru3412i can't solve too
Excited for the next video!!
Coming soon!
Can you make a server using lora so that chatgpt ( current project )can connect to the internet so we can use voice to text / chatgbt text to voice
In file included from c:\Users\brkac\OneDrive\Documents\Arduino\libraries\ESP32-audioI2S-master\src\Audio.cpp:15:0:
c:\Users\brkac\OneDrive\Documents\Arduino\libraries\ESP32-audioI2S-master\src\opus_decoder/opus_decoder.h:7:20: fatal error: memory.h: No such file or directory
compilation terminated.
exit status 1
Uploaded the code successfully but on running it shows the following error:
E (533) I2S: i2s_check_set_mclk(253): ESP32 only support to set GPIO0/GPIO1/GPIO3 as mclk signal, error GPIO number:1073423152
E (534) I2S: i2s_set_pin(314): mclk config failed.
please help
when i run this code it says:C:\Users\home\Documents\Arduino\sketch_stem\Speech_To_Text_ESP32.ino:2:31: fatal error: CloudSpeechClient.h: No such file or directory
compilation terminated.
exit status 1
Compilation error: CloudSpeechClient.h: No such file or directory
what should i do to fix this
Did you fix this?
Hello, I have problems installing the librery, help!
do have the video ESP 32 capture photo able to turn on led and have save data on adafruit
bro it is not working because the libaries are updatd and i can t put
Just wait for tomorrow’s video
It will be a great update for STT
How can i extract the text and put it in the firebase?
Where is the description bro 😑
Will google cloud cut money from the bank account later??
hye i am going to make the project that using ESP 32 that connect to adafruit ...
Hi guys I have a doubt, what if the 90 days google cloud services gets over and the amount will be auto debited ? Or we just provide the card details to get the $300 ?
Dont worry its 300 free credit, and you wont be charged after 90 days, it just stops. Me and my friends have tried it
Is Speech to text charge while free trial??
good job. did you try the offline module?
I am a student trying to learn these kind of stuff. these are a lot of codes, should i upload the code one by one or at the same time in one code?
You just need to upload .ino code, the rest of the code will automatically be included as they are separate header files included in main .ino code. You just need to make sure all of these codes are in same directory.
Bro, This project is not working I have tried 3-4 times but not able to convert speech to text
What's the error?
can i have it as an audio output to my earpiece ?
Maybe if you configure the code and hardware with a module that has an audio jack on it.
I am not able to get the transcribe using the code deployed on the board , after recording it is giving mein Json without transcribed data into it , Please help for the same if anyone faced the similar issue
I have same problem, did u fix it?
@@DropThatGOAL no its buggy , there is some problem with the library. I build the code on python and deployed it on raspberry pi
In my output i am not getting any results promt only totalbilled time. Can u help me??
did you solve this problem? i have the same issue
esp32 can run chatgpt? thats amazing!
We can use vosk api
Hi brother 👋 how r U ?
All good
Hope you enjoyed the video…
I can’t downgrade the Esp32 to 1.0.6
Yes it is not showing
The program can't do anything with the json data
how can i fix this
[HTTPS] GET... failed, error: connection refused
how to solve this? ( I have tested chatgpt api in postman, it is working there but not in code)
try with some other model of the open ai as text-davinci-003 is no more supported by open ai
Did you solve it bro
Please integrate it with chat gpt
I can do that but how much you are ready to pay for it?
Coming soon on our channel….
Is it possible to get voice recog on esp32 without being connected to online services?
No :)
@@josephgeorge3204elechouse have done it with a simple IC, Google it. So why shouldn't it be possible on the more advanced ESP32? in the 1990s people did it with basic stamps with some extra IC..
Speech to text- send to AI- the Text to speech
Yes
Coming up soon on this channel…
Yeah 👍
can't wait awesome project
Ty for the video
Btw why don't u use new ide
Wow 😳
Why not use OpenAI whisper?
Can you share some links
can you make this video in hindi , i need this information ,
Hey Sachin, I tried this out but it is only giving me the request id and total billed time as output. Their is no "result" output that I can see in the json data. Please help me out. Thank you.
I'm having the same problem too, please could you help @Sachin
Try wiring the jumper wire from l/r to VDD rather than GND. I think the wiring schematic in this video is incorrect. In a later project the schematic is wired differently. I swapped the l/r to GND(black-) around to l/r to VDD(red+) to match the later project (The virtual assistant I think) and it worked fine after that.
Solved???
Please tell me
@@Nocturnal3D Thank you very much it worked, I really appreciate it 🙏
Good job brader.
How to use a condenser mic
You need to use MEMS microphone only like this - www.techiesms.com/product/inmp441-microphone-module-i2s/
Hi Json dont answer the words I speak, How can I fix this ?
Okie i fix with wire jumper L/R to VDD and it works thx Nocturnal3d's comment
Can u please explain
i mean I try to write response and keyword on json.file and it doesnt show the words i speak @@karthikn1126
so I trried to wire jumper L/R to vdd to ground and it works so fine@@karthikn1126
They were asking 1000rs not 2rs 😢
please make videos using esp ide
Amazing hack 👏 ❤
great !!!!
Connection failed😢
Same
Me too, is google the problem but i dont knlw how to solve it
its solved or no?
@@StevFoz no
did u rectify this ?
Love you bro ❤
Love you too ✌️
Acchi video hai
Thanks 🤘🏻
Is Prem Vivah mein Chandigarh mein sab koi aaega apna Ghar devasi ka idhar hai apna Bharat Desh ka sab rahega
Hello Sachin
Hello buddy
Do share the video if you like it ✌️
Hi sachin
Hi DrElectronics
Hope you enjoyed the video
Kese ho sachin
Me badhia Hu
Video share jarur krna
please
I didn’t understand a single word you said even though I think it was supposed to be English.
my output.......speech to text not show.....please help
Record start!
Recording Completed. Now Processing...
My Answer - HTTP/1.1 200 OK
Content-Type: application/json; charset=UTF-8
Vary: X-Origin
Vary: Referer
Date: Tue, 30 Jan 2024 18:30:24 GMT
Server: ESF
Cache-Control: private
X-XSS-Protection: 0
X-Frame-Options: SAMEORIGIN
X-Content-Type-Options: nosniff
Alt-Svc: h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
Accept-Ranges: none
Vary: Origin,Accept-Encoding
Transfer-Encoding: chunked
44
{
"totalBilledTime": "3s",
"requestId": "8554249765596014235"
}
0
394
Json daata--{
"totalBilledTime": "3s",
"requestId": "8554249765596014235"
}
0
Bro did you solve it?
Did solve it
@@karthikn1126
I solved it
your wiring may be the problem
@@karthikn1126
try to connect L\R pin to vcc instead of Gnd
@@ebrahemkhalifa3675 what's wrong with you😑
bro i am at the edge of my project and need some assistance , i am receiving an error
error: macro "pgm_read_byte" passed 4 arguments, but takes just 1
return pgm_read_byte(I2S_NUM_0, (char *)data, numData, portMAX_DELAY);
/tmp/3378378928/Speech_To_Text_ESP32/I2S.cpp: In member function 'int I2S::Read(char*, int)':
/tmp/3378378928/Speech_To_Text_ESP32/I2S.cpp:58:10: error: 'pgm_read_byte' was not declared in this scope
return pgm_read_byte(I2S_NUM_0, (char *)data, numData, portMAX_DELAY);
Hello did you ever resolve your error Sir?
Downgrade your ESP32 Version to 1.06
Hey! This is regarding sim800l with esp8266. My nodemcu board resets whenever I send message via sms using the gsm module. Do you know a reason for this?🥲