voice_of_the_doctor.py

import os
from gtts import gTTS
from dotenv import load_dotenv

load_dotenv()

def text_to_speech_with_gtts_old_no_autoplay_functionality(input_text , output_file):
    language = 'en'

    gttsObj = gTTS(
        text=input_text,
        lang=language,
        slow=False
    )
    gttsObj.save(output_file)

text = "hello this is me danish with ai voice"
text_to_speech_with_gtts_old_no_autoplay_functionality(input_text=text,output_file= "output_gtts.mp3")


# import elevenlabs
# from elevenlabs.client import ElevenLabs

# ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY")

# def text_to_speech_with_elevenlabs_old_no_autoplay_functionality(input_text , output_file):
#     client = ElevenLabs(api_key = ELEVENLABS_API_KEY)

#     audio = client.text_to_speech.convert(
#         text = input_text,
#         voice_id = "sunJnCSgZmOuefCgCWBd",
#         model_id = "eleven_turbo_v2",
#         output_format = "mp3_22050_32"
#     )
#     elevenlabs.save(audio , output_file)

# text_to_speech_with_elevenlabs_old_no_autoplay_functionality(input_text=text,output_file= "output_elevenlabs.mp3")




import subprocess
import platform
from pydub import AudioSegment


def text_to_speech_with_gtts_new_autoplay(input_text , output_file):
    language = 'en'

    #create gtts object
    gttsObj = gTTS(
        text=input_text,
        lang=language,
        slow=False
    )
    #save the audio file
    gttsObj.save(output_file)

    #converstion from mp3 to wav
    wav_file = output_file.replace('.mp3', '.wav')
    AudioSegment.from_mp3(output_file).export(wav_file,format="wav")
    # Optionally remove the original mp3 file
    # os.remove(output_file)
    # Play the wav file based on the operating system
    os_name = platform.system()

    try:
        if os_name == "Darwin":
            subprocess.run(['afplay', wav_file])
        elif os_name == "Windows":
            subprocess.run(['powershell', '-c', f'(New-Object Media.SoundPlayer "{wav_file}").PlaySync();'])
        elif os_name == "Linux": 
            subprocess.run(['aplay', wav_file]) 
        else:
            raise OSError("Unsupported operating system")
    except Exception as e:
        print(f"An error occurred while trying to play the audio: {e}")

text = "hello this is me danish with ai voice"
text_to_speech_with_gtts_new_autoplay(input_text=text,output_file= "gtts_testing_autoplay.mp3")


# def text_to_speech_with_elevenlabs_new_autoplay(input_text , output_file):
#     client = ElevenLabs(api_key = ELEVENLABS_API_KEY)

#     audio = client.text_to_speech.convert(
#         text = input_text,
#         voice_id = "sunJnCSgZmOuefCgCWBd",
#         model_id = "eleven_turbo_v2",
#         output_format = "mp3_22050_32"
#     )
#     elevenlabs.save(audio , output_file)

#     wav_file = output_file.replace("mp3", "wav")
#     AudioSegment.from_mp3(output_file).export(wav_file,format="wav")

#     # os.remove(output_file)


#     os_name = platform.system()
#     try:
#         if os_name == "Darwin":
#             subprocess.run(['afplay', wav_file])
#         elif os_name == "Windows":
#             subprocess.run(['powershell', '-c', f'(New-Object Media.SoundPlayer "{wav_file}").PlaySync();'])
#         elif os_name == "Linux": 
#             subprocess.run(['aplay', wav_file]) 
#         else:
#             raise OSError("Unsupported operating system")
#     except Exception as e:
#         print(f"An error occurred while trying to play the audio: {e}")


# text = "hello this is me danish with ai voice"
# text_to_speech_with_elevenlabs_new_autoplay(input_text=text,output_file= "output_elevenlabs_autoplay.mp3")