GPT-4o API: Crash Course for Beginners

Поделиться
HTML-код
  • Опубликовано: 25 янв 2025

Комментарии •

  • @danson3038
    @danson3038 8 месяцев назад +7

    Thx Mervin, would be nice to see the cost of the tests done.

  • @Winchawa
    @Winchawa 8 месяцев назад +1

    Man you are quick Thank you for all of the content you put out..🙏

  • @Yaw_Dev
    @Yaw_Dev 3 месяца назад

    "This is amazing!" Mervin's favorite intro.. lol Greate video..

  • @60pluscrazy
    @60pluscrazy 8 месяцев назад +1

    Wow, Mervin you are amazing. Your videos are truly a value addition 🎉🎉🎉🎉

  • @NovATriX
    @NovATriX 8 месяцев назад +2

    How can we output TTS audio with emotions like they shown in the GPT-4o keynote? When I look at the OAI docs it only show the old TTS model.

  • @Copa20777
    @Copa20777 8 месяцев назад

    Thanks mervin, am glad to have moved with you in Ai till this point, your tutorials have made me a better Ai user

  • @zephyrrjl
    @zephyrrjl 7 месяцев назад +1

    when I try to export my openai key it gives me an error saying:
    The term 'export' is not recognized as the name of a cmdlet, function, script file, or operable program.
    Check the spelling of the name, or if a path was included, verify that the path is correct and try again.

  • @supercurioTube
    @supercurioTube 8 месяцев назад +3

    Thanks for the quick overview, it was easy to follow.
    Can you give an idea of how long it took to process the video and audio? We couldn't tell from the edited version.

    • @Bangs_Theory
      @Bangs_Theory 8 месяцев назад +2

      That's a good question, I was wondering the same thing.

  • @asqu
    @asqu 8 месяцев назад

    6:47 audio transcription with Whisper-1 model ???? Then GPT-4o does not process audio ???? After all, it was all supposed to be implemented in one model, in one neural network. Is it the TTS engine that is a separate model too?

    • @Bangs_Theory
      @Bangs_Theory 8 месяцев назад

      Perhaps Merlin didn't realize he didn't need the Whisper-1 model or simply was trying to save money.

    • @EachDayForever
      @EachDayForever 8 месяцев назад +1

      They just haven’t publicly released its audio capabilities yet! That’s the only reason.

  • @chrisder1814
    @chrisder1814 4 месяца назад

    hello can it remove the background from my images that are in my database

  • @MathiasCzaja
    @MathiasCzaja 7 месяцев назад

    Hello, i really appreciate your work. What is the estimated price for image processing within gpt4o api? How much you have paid for those triangle picture?

  • @cgc2300
    @cgc2300 8 месяцев назад

    hello I am in France and the Voice function does not work at all as it works in the demonstration video

  • @firaskhamis5075
    @firaskhamis5075 5 месяцев назад

    i noticed that the model when access through api does not have a access to real time data, is that true?

    • @MervinPraison
      @MervinPraison  5 месяцев назад

      No model will have real time data. Real time data will be available to any model via tools

  • @jelliott3604
    @jelliott3604 8 месяцев назад

    Assume audio only didn't find anything as the audio only doesn't have any input that tells it that the voice is that of Sam Altman so it's looking for a reference to him in the content

  • @micbab-vg2mu
    @micbab-vg2mu 8 месяцев назад +1

    thank you for the video:)

  • @Beenee_AI
    @Beenee_AI 8 месяцев назад +5

    So, please give me a reason to pay for chatgpt pro...

    • @Create-The-Imaginable
      @Create-The-Imaginable 8 месяцев назад

      Artificial Super Intelligence! I think they have it and this is just a tease! Think about it!

    • @asiddiqi123
      @asiddiqi123 8 месяцев назад +1

      Custom Gpt plus rate limits

    • @OumarDicko-c5i
      @OumarDicko-c5i 8 месяцев назад

      ​@@asiddiqi123I think custom gpt will be free too but only more rate limit

    • @nani3209
      @nani3209 8 месяцев назад +4

      For voice assistant

  • @hassanahmad1483
    @hassanahmad1483 8 месяцев назад

    what is use of these...if we cant deploy?

  • @pragyantiwari3885
    @pragyantiwari3885 8 месяцев назад +2

    I just passed some integral questions to solve....got wrong answers though!😐

    • @luisgustavosantini6843
      @luisgustavosantini6843 8 месяцев назад +2

      Actually, I did the same... But to be more accurate, ask to him do this using python libraries! Or change the temperature to Zero

    • @morespinach9832
      @morespinach9832 8 месяцев назад

      @@luisgustavosantini6843temperature to 0 or to 1?

  • @Kira-fj8el
    @Kira-fj8el 8 месяцев назад

    Need a new video for assistant api with new features.I need to know how to control token count?????

  • @MeinDeutschkurs
    @MeinDeutschkurs 8 месяцев назад

    Input tokens will explode? Yes, great. Yes, why paying plus anymore…

  • @asiddiqi123
    @asiddiqi123 8 месяцев назад

    Marvin ia Chuck Norris of LLMs

  • @mohamedkeddache4202
    @mohamedkeddache4202 8 месяцев назад

    is the API free ?

    • @24-7gpts
      @24-7gpts 8 месяцев назад

      I wish 😂

  • @tonywhite4476
    @tonywhite4476 8 месяцев назад +1

    See, this is what I meant. While we play around with, testing and leaderboards and oo-ah videos, OpenAI is build stuff and know we have watch more videos about what they built instead of building it ourselves. Everything was there, Groq, Whisper, gpt vision, etc. you want to make a lot of videos about nothing, go ahead.

    • @farexBaby-ur8ns
      @farexBaby-ur8ns 8 месяцев назад

      Well these vids improve upon your understanding and build upon prev knowledge. There might be overlaps with langchain APIs - and there will be wrappers

  • @dareljohnson5770
    @dareljohnson5770 8 месяцев назад

    This is scary. It could be turned into the ultimate surveillance tool.