ai_speech_research_papers/play.py

# Written by retoor@molodetz.nl

# This source code initializes a Text-to-Speech (TTS) engine, plays text as audio using the TTS engine, and plays audio files using both the VLC media player and PyAudio.

# Libraries imported: 'pyaudio', 'wave', 'pyttsx3', 'functools', 'os', 'simpleaudio'

# The MIT License (MIT)
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

import pyaudio
import functools
import os
import subprocess
import sys
import pygame 





def play_audio(filename):
    pygame.mixer.init()
    pygame.mixer.music.load(filename)
    pygame.mixer.music.play()
    while pygame.mixer.music.get_busy():
        pygame.time.Clock().tick(10)


def play_audio2(filename):
    ffmpeg_cmd = [
        "ffmpeg",
        "-i", filename,
        "-f", "s16le",
        "-ar", "44100",
        "-ac", "2",
        "pipe:1"
    ]
    process = subprocess.Popen(ffmpeg_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, bufsize=10**6)

    p = pyaudio.PyAudio()
    stream = p.open(
        format=p.get_format_from_width(2),
        channels=2,
        rate=44100,
        output=True
    )
    chunk_size = 4096
    try:
        while True:
            data = process.stdout.read(chunk_size)
            if not data:
                break
            stream.write(data)
    finally:
        stream.stop_stream()
        stream.close()
        p.terminate()
        process.stdout.close()
        process.wait()