[METHOD] Get Human-like Text To Speech Voices

[444444]

WOW! High quality share. Love this TTS. Thank you so much

 

[korunovski]

text to speech allowed in youtube but not monitized

Oh yes it is. Check out Radio TTS on youtube.

 

[SurZodoY]

Thanks for sharing and all the replies also held valuable info about the use of it

 

[silentpat]

great one!
Another tip is aws polly. It can be used for free through api for about 1000-req per day.

 

[Zeldar]

Not bad, might be useful. Thank you for the share.

 

[Deleted member 283687]

Great share

 

[thatkid1]

Try aws polly, they are really good.

 

[hoangvinhcbvn]

anyone are using https://www.naturalreaders.com/commercial.html ?
The voice of reader *guy in this tool is most human voice likely I ever seen.
but $99/month is too expensive

 

[HustleForLife]

anyone are using https://www.naturalreaders.com/commercial.html ?
The voice of reader *guy in this tool is most human voice likely I ever seen.
but $99/month is too expensive

Still cheaper than those overpriced fiverr voice actors.

 

[korunovski]

anyone are using https://www.naturalreaders.com/commercial.html ?
The voice of reader *guy in this tool is most human voice likely I ever seen.
but $99/month is too expensive

That's absolutely trash. https://www.ibm.com/demos/live/tts-demo/self-service/home
Try the Henry voice

 

[Topgallant01]

Great share... Useful

 

[AAW]

Still cheaper than those overpriced fiverr voice actors.

Haha

 

[silentpat]

I found this in my archive. Maybe someone finds it useful? Can be run from terminal. I used it for radio commercials. It became really good!

Spoiler: PHP POLLY SYNTHESIZE SPEECH

<?php
/**
USAGE

1. You must have composer installed, if not, https://getcomposer.org
2. in a terminal, run `composer install`
3. Change to your aws keys in the top of the file. You can signup on AWS for free.
4. change text and output file and voice in function synthesizeSpeech

*/

putenv("AWS_ACCESS_KEY_ID=xxxxxxxxxxx"); // replace xxxx with your access key (free)
putenv("AWS_SECRET_ACCESS_KEY=xxxxxxxxxxxx"); // replace with your secret key

require_once(__DIR__ . "/vendor/autoload.php"); // autoload all dependencies
use Aws\Exception\AwsException;
use Aws\Polly\PollyClient;

/**
* Calls polly and saves speechfile to outputfile
*/
function synthesizeSpeech($text, $outputfile, $voice = "random") {
    $voices = [
        "Geraint",    "Gwyneth",    "Mads",    "Naja",    "Hans",    "Marlene",    "Nicole",    "Russell",    "Amy",    "Brian",    "Emma",    "Raveena",    "Ivy",    "Joanna",    "Joey",    "Justin",     "Kendra",     "Kimberly",     "Matthew",     "Salli",     "Conchita",     "Enrique",
         "Miguel",     "Penelope",     "Chantal",     "Celine",     "Lea",     "Mathieu",     "Dora",     "Karl",     "Carla",     "Giorgio",     "Mizuki",     "Liv",     "Lotte",     "Ruben",     "Ewa",     "Jacek",     "Jan",     "Maja",     "Ricardo",     "Vitoria",      "Cristiano",
         "Ines",     "Carmen",     "Maxim",     "Tatyana",     "Astrid",     "Filiz",     "Vicki",     "Takumi",     "Seoyeon",     "Aditi",     "Zhiyu",     "Bianca",     "Lucia",     "Mia"
    ];
    if($voice == "random")$voice = $voices[ rand(0,count($voices)-1)];
    $format = "mp3";
    $credentials = new Aws\Credentials\Credentials(getenv('AWS_ACCESS_KEY_ID'), getenv('AWS_SECRET_ACCESS_KEY'));
    $client = new Aws\Polly\PollyClient([
        'version' => '2016-06-10',
        'region' => 'us-east-2',
        'credentials' => [
            'key'    => getenv('AWS_ACCESS_KEY_ID'),
            'secret' => getenv('AWS_SECRET_ACCESS_KEY'),
        ],
    ]); 
    try {
        $result = $client->synthesizeSpeech([
            'Text' => $text,
            'TextType' => 'text',
            'OutputFormat' => $format,
            'VoiceId' => $voice,
  
        ]);
        $song = $result->get('AudioStream')->getContents();
        file_put_contents($outputfile, $song);
    } catch (AwsException $e) {
        // output error message if fails
        echo $e->getMessage();
        echo "\n";
    } 
}

// example one, write one file
synthesizeSpeech("Get fifty-percent discount. Sign up today.", "output.mp3", "random");

// example two, synthesize a whole book
$files=[
    'chapter1.txt',
    'chapter2.txt',
    'chapter3.txt',
       ];

foreach($files as $file) {
    $data = file_get_contents(__DIR__."/".$file);
    synthesizeSpeech($data, $file.".mp3", "Astrid");
    die();
}

 

[bosses]

Thanks

 

[Donomar]

WOW! High quality share. Thanks

 

[Blacman]

Thank you. Awesome share. I will use in my youtube videos.

So how can you add it to your YouTube video

 

[Blacman]

is IBM gonna come after you if you use if for commercial purpose? I want to pair it with youtube + affiliate marketing.

How are you planning on adding the voice to YouTube video. I really want to try it out

 

[olegnaxd]

Thanks for the gudie, very usefull

 

[sony1]

How are you planning on adding the voice to YouTube video. I really want to try it out

First you write the script, then paste the text into website and generate the mp3 file which you'll add to your video file in any video editing software.

 

[nvlima09]

how to download de audio file?