How to generate more MP3 files at the same time in Amazon Polly using Python code?

[makiwara]

Hi!

The programming language of Amazon Polly (TTS) is Python. However, I'm not very familiar with it yet.

I have a list with words and want Amazon Polly to pronounce them and save every word as a new mp3 file. (name could be the word's name)

My list is like:

"
apple
banana
peach
orange
...
"

On the following website there is a code provided by Amazon which result is more mp3 file so seems promising: (I inserted it at the end of my post)
https://aws.amazon.com/blogs/machine-lea...on-script/

My question is, how can I modify that code, so I can use it to generate the pronouncation for each word as a new mp3 file?

Thank you for your help! It means to me a lot!

Have a very nice day!

____

# coding: utf-8
import subprocess
import codecs

f = codecs.open("story.txt", encoding='utf-8')

cnt = 0
file_names = ''

for line in f:
    rendered = ''
    line = line.replace('"', '\\"')
    command = 'aws polly synthesize-speech --text-type ssml --output-format "mp3" --voice-id "Salli" --text "{0}" {1}'

    if '\r\n' == line:
        #A pause after a paragraph
        rendered = '<speak><break time= "2s"/></speak>'
    else:
        #A pause after a sentence
        rendered = '<speak><amazon:effect name=\\"drc\\">' + line.strip() + '<break time=\\"1s\\"/></amazon:effect></speak>'
    
    file_name = ' polly_out{0}.mp3'.format(u''.join(str(cnt)).encode('utf-8'))
    cnt += 1
    command = command.format(rendered.encode('utf-8'), file_name)
    file_names += file_name
    print command
    subprocess.call(command, shell=True)

print file_names
execute_command = 'cat ' + file_names + '>result.mp3'
subprocess.call(execute_command, shell=True)

execute_command = 'rm ' + file_names
print 'Removing temporary files: ' + execute_command
subprocess.call(execute_command, shell=True)

[gontajones]

Please, tell us what is happening? Output and errors of your script.

Your mp3 file name is resulting in polly_out'X'.mp3, this is not good.
Change it to something like:

file_name = ' polly_out_{0}.mp3'.format(cnt)

---

I think that what you want is exactly those polly_out_X.mp3 files, right?
But at the end of your script you're removing them from your system and staying only with the result.mp3.

[makiwara]

Hi Gontajones, thank you for your answer and sorry for the late reply!

I was reading about the topic, hoping that I can ask better questions.

As far as I know, the last part of the code unites the generated mp3 files into 1 big mp3 file. (the amazon article which I have linked says so at least) So that part could be deleted (?), since I need a new mp3 file for each line in my txt file.

So my txt file is something like:

orange and fruit
vegetables
citrone
peach
...

And the output's name could be the number of the row, containing the following content:
So 1.mp3 = "orange and fruit"
2.mp3 ="vegetables"
3.mp3 = "citrone"
4.mp3 = "peach"

And so on.

I really appreciate your help, since this whole Python language is new to me.

It means to me a lot!

Have a nice day!

Please, tell us what is happening? Output and errors of your script.

Your mp3 file name is resulting in polly_out'X'.mp3, this is not good.
Change it to something like:

file_name = ' polly_out_{0}.mp3'.format(cnt)

---

I think that what you want is exactly those polly_out_X.mp3 files, right?
But at the end of your script you're removing them from your system and staying only with the result.mp3.