Convert Text To Real Human Speech With Google Cloud Text-To-Speech API In Python

Google Text-to-Speech is a cloud service by Google that turns text into natural-sounding speech. Using advanced machine learning, it offers a variety of voices and languages, making digital content more engaging and accessible to a wide audience. In this tutorial, we are going to learn how to get started with Google Cloud Text To Speech API in Python.
📋 Source Code: / source-code-text-10231...
📋 Voice List: cloud.google.com/text-to-spee...
📋 GCP Text-To-Speech Pricing: cloud.google.com/text-to-spee...
► Buy Me a Coffee? Your support is much appreciated!
-------------------------------------------------------------------------------------------
☕ Paypal: www.paypal.me/jiejenn/5
☕ Venmo: @Jie-Jenn
💸 Join Robinhood with my link and we'll both get a free stock: bit.ly/3iWr7LC
► Support my channel so I can continue making free contents
---------------------------------------------------------------------------------------------------------------
🛒 By shopping on Amazon → amzn.to/2JkGeMD
👩‍💻 Follow me on Linked: / jiejenn
🌳 Becoming a Patreon supporter: / jiejenn
✉️ Business Inquiring: KZread@LearnDataAnalysis.org
00:00 - Intro & Demo
02:44 - Pricing
03:56 - Create a Google Cloud project (optional)
05:05 - Enable GCP Text-To-Speech API
05:35 - Create a service account
08:25 - Text-To-Speech Python script development
#gcp #googlecloud #python #texttospeech

Пікірлер: 33

  • @melhoresofertasapp
    @melhoresofertasapp3 ай бұрын

    Great video, this is the best I have found!

  • @jiejenn

    @jiejenn

    3 ай бұрын

    Thanks for the comment!

  • @AlexRodriguez-vl1ec
    @AlexRodriguez-vl1ec4 ай бұрын

    My code works fine but whenever I try to change the speaking rate it does not work. I have tried to find more documentation on it but I cannot figure out why it will not register. If I go outside the range it will come up with an error, which means it does know what float number I am using. Does changing the speaking rate work for you?

  • @anavildidthasom6201
    @anavildidthasom62012 ай бұрын

    Really good tutorial!

  • @jiejenn

    @jiejenn

    2 ай бұрын

    👍

  • @fabiolazza8182
    @fabiolazza8182Ай бұрын

    I was lost when you started explaining the Python Env script. So how do you initialize it ? Could you please detail that step for me ?

  • @sebastianrodriguez672
    @sebastianrodriguez6722 ай бұрын

    So useful, thanks

  • @jiejenn

    @jiejenn

    2 ай бұрын

    👍

  • @user-hq4im9wb8k
    @user-hq4im9wb8k2 ай бұрын

    hi does it work like you give the text and it converted to the mp3 then you play? If i give everytime new text so it will create that mp3????

  • @jiejenn

    @jiejenn

    2 ай бұрын

    You can. I have done it with most of TTS APIs.

  • @dickiie9970
    @dickiie99702 ай бұрын

    has the pricing changed? as of 1st of May 2024, it says that text to speech on-device per device USD XX.XX , this means that every device that use this API, have to pay x amount?

  • @jiejenn

    @jiejenn

    2 ай бұрын

    Can you share the source?

  • @user-qr8ob4dz5g
    @user-qr8ob4dz5g4 ай бұрын

    hi. how long at most the desired text strings can be? i want to create mp3 for 10hour audiobook from a 85000 words text file as input. tnx

  • @jiejenn

    @jiejenn

    3 ай бұрын

    The limit is 5000 bytes per request. You will need to chunk the audio file individually. cloud.google.com/text-to-speech/quotas

  • @engitix
    @engitix4 ай бұрын

    Which python version do you use?

  • @jiejenn

    @jiejenn

    4 ай бұрын

    Currently Python 3.10. Looking to upgrade to Python 3.12 soon.

  • @HideBuz
    @HideBuz2 ай бұрын

    Can you go into how to chunk so that sentences are not broken up?

  • @jiejenn

    @jiejenn

    2 ай бұрын

    Not sure if I understand your question.

  • @HideBuz

    @HideBuz

    2 ай бұрын

    @@jiejennMy bad: "Can you go into the chunking of texts, so that sentences are not broken up / split into the middle in order to solve the google api max chunk size problem?" Also how can we generate a single large audiofile instead of many small chunks the the google api returns? I would appreciate a version 2 of the video with improved code on how to deal with the api limit. Many thanks! You earned a sub!

  • @Legend.-.
    @Legend.-.2 күн бұрын

    Can we stream the response of google text to speech?

  • @jiejenn

    @jiejenn

    Күн бұрын

    Yes, you can.

  • @Legend.-.

    @Legend.-.

    Күн бұрын

    @@jiejenn ohh, can you share any resources for doing it? I am trying to accomplish it but its not working for me.

  • @jiejenn

    @jiejenn

    Күн бұрын

    ​@@Legend.-. I need to check if I still have the script. I will let you know.

  • @w.davidwilliams2544
    @w.davidwilliams2544Ай бұрын

    I am not a Python expert. Can someone help me set it up?

  • @shakil_ilham

    @shakil_ilham

    Ай бұрын

    Hi. I can help you.

  • @minhsenma
    @minhsenma5 ай бұрын

    Please makw video add drop shadow to around app

  • @jiejenn

    @jiejenn

    5 ай бұрын

    Can you be more specific? Not sure if I understand what you mean.

  • @minhsenma

    @minhsenma

    5 ай бұрын

    @@jiejenn yes add style specific to widget and add custom style to mainwindow drop shadow border ...

  • @ribeiro4642
    @ribeiro46422 күн бұрын

    Wouldn't it be easier to create an API key? 05:45

  • @jiejenn

    @jiejenn

    2 күн бұрын

    @@ribeiro4642Only a limited services support API key, TTS is not one of them.

  • @ribeiro4642

    @ribeiro4642

    2 күн бұрын

    @@jiejenn I'm using Google's TTS via API. This made things much simpler.

  • @dantesbytes
    @dantesbytes3 ай бұрын

    :(