Best Open Source Text-to-Speech AI Tutorial in 2024

Поделиться
HTML-код
  • Опубликовано: 18 ноя 2024
  • НаукаНаука

Комментарии • 63

  • @jochenrunge3706
    @jochenrunge3706 2 месяца назад +10

    Ok I'm only 19seconds in but I have to pause here to tell U smth I hope maybe makes U smile a bit. UK in south park tech support is always an Indian worker and ik that india is actually very advanced in tech nowadays Ur country worked hard to get there and don't think the rest of the world doesn't notice. Even if we in Europe make fun of it I swear to god U won't find a single programmer in Germany that doesn't watch Indian tech tutorials. We are very grateful that U guys are making these amazing videos because our country for example is insane far behind and without people like you even the young people that want to learn are not having it easy because the generation teaching us is often times behind their students in terms of capabilities. Yes we make fun but we all respect U and even if Indian accent is funny ours isn't better and Indian English is one of the accents that's very clear and easy to understand. In school the listening parts for young kids in tests is sometimes with Indian accent and every time it's Indian there's a focking train or car passing by or faking helicopter sounds or whatnot because U Guys are that easy to understand. I probably would have an easier time communicating driving on top of an Indian train than beeing to dinner was an American guy. You guys are amazing we have huge respect and admire Ur guys effort and are grateful for your service to the education and evolution of the tech community. Don't be sorry for Ur accent wear it with pride my friend

    • @1littlecoder
      @1littlecoder  2 месяца назад +2

      Thanks so much man! That's very kind of you to say this!

  • @pareak
    @pareak 3 месяца назад +4

    This video is right in time. I am working on a local chatbot with speech output.

  • @antonpictures
    @antonpictures 3 месяца назад +9

    indians are the best at coding. fact. you sounded so good i subscribed

  • @zechariahprince5671
    @zechariahprince5671 20 дней назад +1

    bruh your voice is fine, don't feel like you are hard to understand. I only speak english and never have an issue understanding you

    • @1littlecoder
      @1littlecoder  20 дней назад

      @@zechariahprince5671 thanks bruh!

  • @generalfishcake
    @generalfishcake 2 месяца назад +3

    It's such a shame Coqui TTS shut down. It was by far the best to use, and the outputs were amazing. Any news of a clone/fork?

  • @sagarangadi5677
    @sagarangadi5677 3 месяца назад

    Thank you for introducing this model, gonna use this for my product. Just a suggestion, there are very less tuttorials on youtube where they take a model and show how to implement the models in project, these tuttorials will give your channel a lot of power and also very helpful for begginers, would love to see more of such kind...

    • @1littlecoder
      @1littlecoder  3 месяца назад

      I used to have a bunch of tutorials like that, like implementing a talking chatbot. do you mean like that or something else?

    • @sagarangadi5677
      @sagarangadi5677 3 месяца назад

      @@1littlecoder Yeah just like when any new great models are coming out then just making tutorials of implementing those models into real world application, software products.... Like in this tutorial you explained using google collab, just like that we can have other tutorial like how to implement this model if we are making a software product for real users, like using real coding, implementing these models.... I actually checked your all videos and there already a lot of videos you have uploaded as tutorials, hope to see more of such videos which will teach how to implement these models using coding in actual projects, because honestly all this tech is so new at least for indians it is very new and most of the people don't understand what's written in documentation and all, so everybody who wants to build some application and want to use these models will turn to video tutorials like yours, and majority of creators are just going with the hype and creating content on AI that just has news and hype about AI models, very less videos on actual detailed implementation of these models in real coding projects, so it would be great to see real implementation of these models in coding projects like example 'How to implement Parler-TTS model in your node.js project or in any kind of actual project' where in this tutorial you will explain the implementation of the model in a code editor while writing the code to implement it using python language or any required language. Hope you got an approx picture of what I'm saying 😄 ........and to be honest you are one of the very rare AI related creators from India who actually goes into technical, and I never miss any of your videos, Thanks for your contribution to our learning ❤

  • @K4leidos
    @K4leidos 2 месяца назад

    Don't be so harsh on yourself. Your voice is much better than the AI voice you demo'd in the beginning. MUCH better.

  • @__________________________6910
    @__________________________6910 3 месяца назад +2

    You look smart after getting your hair cut. It's been a week since I last saw you.

  • @davidtindell950
    @davidtindell950 2 месяца назад +1

    Thank You. Timely and Useful !

  • @012_siddhantprasad9
    @012_siddhantprasad9 3 месяца назад +1

    Nice tool, need more on this tool

  • @siddhubhai2508
    @siddhubhai2508 2 месяца назад +1

    If you would be wearing earbuds or headphones you would realize that the generated audio through AI was majorly running only on the left channel of pair !!

  • @free_thinker4958
    @free_thinker4958 3 месяца назад +5

    Can we run it on cpu??

  • @puneet1977
    @puneet1977 3 месяца назад +2

    Fine tuning my own voice on this model will be interesting

  • @davidtindell950
    @davidtindell950 2 месяца назад +2

    NEW Subscriber: As you recommended, we must experiment with the various speakers and cadences. The "Jon" voice gave me a severe headache :)

    • @1littlecoder
      @1littlecoder  2 месяца назад

      haha thanks for the sub, I'm dropping another TTS very soon!

  • @ps3guy22
    @ps3guy22 3 месяца назад +3

    western 1littlecoder voice jumpscare

  • @testales
    @testales 3 месяца назад

    Very useful to know about this option. I just failed miserably when trying to figure out why the voice with bark are different all the time until I realized that this is by design. I'm not happy with CoquiTTS either, specially when it comes to non-English speakers and Tortoise has it's issue already in its name. There is some hype about AllTalk TTs but that's in it's core just CoquiTTS. Did I miss a major option?

  • @vivekkarumudi
    @vivekkarumudi 3 месяца назад

    i was genuinely fooled the first few secs , i was just thinking maybe you know how to impress the global audience with your new accent.

  • @ShaidaMuhammad
    @ShaidaMuhammad 2 месяца назад

    What languages does it support If I can't fine-tune it?

  • @_rohitgupta_
    @_rohitgupta_ 2 месяца назад

    Great video man! Does it support hindi or other languages as well?

  • @DaVasQ
    @DaVasQ 3 месяца назад +1

    this is a cool tool, could do a video on how to train for foreign language like french ?

    • @DaVasQ
      @DaVasQ 3 месяца назад

      the length of text we can TTS is quite small. is there anything we can fintune to increase this parameter ?

  • @KALYAN1898
    @KALYAN1898 3 месяца назад

    I loved it , I just subscribed,
    Could u please drop a tutorial to fine tune this with regional language like Telugu, Thai or viatnames please …..

  • @hollerith-z5x
    @hollerith-z5x 3 месяца назад +2

    "ED IN BRUH" (not eye-din-burg university)🙂

    • @1littlecoder
      @1littlecoder  3 месяца назад +2

      @@hollerith-z5x oh thank you for correcting. 🙏🏾🙏🏾

  • @dhruvmehta2377
    @dhruvmehta2377 3 месяца назад

    People are using the term artificial intelligence so vagely nowadays can you make a video that explains what actually ai is and what is the difference between having a basic algorithm like Google or youtube and having ai

  • @ChronicleContent
    @ChronicleContent 3 месяца назад

    how do you use it on production app?

  • @lucifer9814
    @lucifer9814 2 месяца назад

    Could you perhaps explain these things from a layman term, because even after watching the entire video, I have no clue how to get this thing running on my computer. Not everyone's a programmer you know.

    • @1littlecoder
      @1littlecoder  2 месяца назад

      @@lucifer9814 thanks for sharing. Could you please explain if there is any particular part that didn't make sense to you

    • @lucifer9814
      @lucifer9814 2 месяца назад

      @@1littlecoder I would actually like to know how to use this software, not learn programming and coding before trying to understand what you're saying in this video. I'm no layman when it comes to computers and whatnot but that doesn't necessarily make me a programmer, so having said that, can you actually tell me how and where do I install this tool from and have it running on my computer.

  • @BiMoba
    @BiMoba 2 месяца назад

    Are there any oss api server for this model, sir?

  • @int8float64
    @int8float64 3 месяца назад

    hey bro, are there any opensource models to enhance audio like in adobe firefly?

  • @gmag11
    @gmag11 3 месяца назад +2

    Is this model trained for multilingual generation

  • @KumR
    @KumR 3 месяца назад +1

    lol..for a second I thought there is some issue with my laptop 🙂

  • @jaycabuguason6067
    @jaycabuguason6067 2 месяца назад

    Can this function even in offline?

  • @SloanMosley
    @SloanMosley 3 месяца назад

    It's a shame that voice cloning is not enabled by default. I am guessing it's a legal issue. I image it's easy to do though. Just like they convert the voice description into vector space to adjust the output, you could do the same with an audio input.

  • @333harsh333sethia
    @333harsh333sethia 3 месяца назад +2

    I feel alibaba's fun-audio-llm's cosyvoice and sensevoice are much better than this.. Opensource and really good models

  • @ogahsunday3691
    @ogahsunday3691 2 месяца назад

    Make a tutorial on how to produce its llama.cpp version so what we can use it for android app inferencing

    • @1littlecoder
      @1littlecoder  2 месяца назад

      I'm no sure if it's easier to convert into a GGUF format, I'll check it out!

  • @anurupmillan
    @anurupmillan 3 месяца назад +2

    Is it better than CoquiTTS?

  • @ashwin2263
    @ashwin2263 3 месяца назад

    Interesting content

  • @mathavansg9227
    @mathavansg9227 3 месяца назад

    Great

  • @zyxwvutsrqponmlkh
    @zyxwvutsrqponmlkh 3 месяца назад

    No, that was not a good voice. Way too high pitch, sounded like a 13 year old.

    • @1littlecoder
      @1littlecoder  3 месяца назад +1

      Seriously? I felt it sounded mature

    • @mshonle
      @mshonle 3 месяца назад +2

      I’m glad the video switched to your real voice! Never change!

    • @zyxwvutsrqponmlkh
      @zyxwvutsrqponmlkh 3 месяца назад

      @@1littlecoder Yeah, that voice at the start, it was weak, non authoritative. TBH if you had that voice from the start of your channel you would have done worse not better.
      Maybe if your audience was children that sort of voice would be ok. But no, it was not a good voice.
      The AI voice over you did ages ago was much much better. It also seemed to capture things like laughter and such better too. This is a downgrade.

  • @thenoblerot
    @thenoblerot 3 месяца назад +1

    omg that voice... lmao no no no...
    *your* voice is just fine smh smooth and rich like ghee 🧈❤

  • @thetrueanimefreak6679
    @thetrueanimefreak6679 2 месяца назад

    what are you talking about i like your voice! W