Audio Livestreaming with Python & Flask

Question

I'm currently strugling with my implementation of a simple live streaming web application using Python and Flask. It seems that I'm not able to stream my live recorded audio from the servers microphone input to the webpage.

server.py

from flask import Flask, render_template, Response
import cv2
import framework
import pyaudio
import audio_processing as audioRec

FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
CHUNK = 1024

audio = pyaudio.PyAudio()


app = Flask(__name__)


@app.route('/')
def index():
    """Video streaming home page."""
    return render_template('index.html')


# Stream routing
@app.route('/video_feed')
def video_feed():
    """Video streaming route. Put this in the src attribute of an img tag."""
    return Response(generateVideo(),
                    mimetype='multipart/x-mixed-replace; boundary=frame')


@app.route("/audio_feed")
def audio_feed():
    """Audio streaming route. Put this in the src attribute of an audio tag."""
    return Response(generateAudio(),
                    mimetype="audio/x-wav")


# Stream generating
def generateVideo():
    """Video streaming generator function."""
    cap = cv2.VideoCapture(0)
    while (cap.isOpened()):
        ret, frame = cap.read()
        output = framework.streamer(frame, 'final')
        cv2.imwrite('signals/currFrame.jpg', output)
        yield (b'--frame\r\n'
               b'Content-Type: image/jpeg\r\n\r\n' + open('signals/currFrame.jpg', 'rb').read() + b'\r\n')


def generateAudio():
    """Audio streaming generator function."""
    currChunk = audioRec.record()
    data_to_stream = genHeader(44100, 32, 1, 200000) + currChunk
    yield data_to_stream

    # with open("signals/audio.wav", "rb") as fwav:
    #     data = fwav.read(1024)
    #     while data:
    #         yield data
    #         data = fwav.read(1024)


def genHeader(sampleRate, bitsPerSample, channels, samples):
    datasize = samples * channels * bitsPerSample // 8
    o = bytes("RIFF",'ascii')                                               # (4byte) Marks file as RIFF
    o += (datasize + 36).to_bytes(4,'little')                               # (4byte) File size in bytes excluding this and RIFF marker
    o += bytes("WAVE",'ascii')                                              # (4byte) File type
    o += bytes("fmt ",'ascii')                                              # (4byte) Format Chunk Marker
    o += (16).to_bytes(4,'little')                                          # (4byte) Length of above format data
    o += (1).to_bytes(2,'little')                                           # (2byte) Format type (1 - PCM)
    o += (channels).to_bytes(2,'little')                                    # (2byte)
    o += (sampleRate).to_bytes(4,'little')                                  # (4byte)
    o += (sampleRate * channels * bitsPerSample // 8).to_bytes(4,'little')  # (4byte)
    o += (channels * bitsPerSample // 8).to_bytes(2,'little')               # (2byte)
    o += (bitsPerSample).to_bytes(2,'little')                               # (2byte)
    o += bytes("data",'ascii')                                              # (4byte) Data Chunk Marker
    o += (datasize).to_bytes(4,'little')                                    # (4byte) Data size in bytes
    return o




if __name__ == '__main__':
    app.run(host='0.0.0.0', debug=True, threaded=True)

audio_processing.py

import pyaudio

FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
CHUNK = 1024

audio = pyaudio.PyAudio()


def record():
    # start Recording
    stream = audio.open(format=FORMAT, channels=CHANNELS,
                    rate=RATE, input=True,
                    frames_per_buffer=CHUNK)
    # print "recording..."
    data = stream.read(CHUNK)
    return data

I'm trying to get the current Chunk of the microphone using the audio_processing.py and using yield to respond the current samples to the user. The video stream works quite good. Anyone knows, what I'm doing wrong here?

Kind regards, Felix

Answer 1

Here is a working example with the inbuilt microphone of your device. Sorry for not being able to explain much, but here's what I figured out for my app!

app.py

from flask import Flask, Response,render_template
import pyaudio

app = Flask(__name__)


FORMAT = pyaudio.paInt16
CHANNELS = 2
RATE = 44100
CHUNK = 1024
RECORD_SECONDS = 5

 
audio1 = pyaudio.PyAudio()
 


def genHeader(sampleRate, bitsPerSample, channels):
    datasize = 2000*10**6
    o = bytes("RIFF",'ascii')                                               # (4byte) Marks file as RIFF
    o += (datasize + 36).to_bytes(4,'little')                               # (4byte) File size in bytes excluding this and RIFF marker
    o += bytes("WAVE",'ascii')                                              # (4byte) File type
    o += bytes("fmt ",'ascii')                                              # (4byte) Format Chunk Marker
    o += (16).to_bytes(4,'little')                                          # (4byte) Length of above format data
    o += (1).to_bytes(2,'little')                                           # (2byte) Format type (1 - PCM)
    o += (channels).to_bytes(2,'little')                                    # (2byte)
    o += (sampleRate).to_bytes(4,'little')                                  # (4byte)
    o += (sampleRate * channels * bitsPerSample // 8).to_bytes(4,'little')  # (4byte)
    o += (channels * bitsPerSample // 8).to_bytes(2,'little')               # (2byte)
    o += (bitsPerSample).to_bytes(2,'little')                               # (2byte)
    o += bytes("data",'ascii')                                              # (4byte) Data Chunk Marker
    o += (datasize).to_bytes(4,'little')                                    # (4byte) Data size in bytes
    return o

@app.route('/audio')
def audio():
    # start Recording
    def sound():

        CHUNK = 1024
        sampleRate = 44100
        bitsPerSample = 16
        channels = 2
        wav_header = genHeader(sampleRate, bitsPerSample, channels)

        stream = audio1.open(format=FORMAT, channels=CHANNELS,
                        rate=RATE, input=True,input_device_index=1,
                        frames_per_buffer=CHUNK)
        print("recording...")
        #frames = []
        first_run = True
        while True:
           if first_run:
               data = wav_header + stream.read(CHUNK)
               first_run = False
           else:
               data = stream.read(CHUNK)
           yield(data)

    return Response(sound())

@app.route('/')
def index():
    """Video streaming home page."""
    return render_template('index.html')

      
if __name__ == "__main__":
    app.run(host='0.0.0.0', debug=True, threaded=True,port=5000)

index.html - under templates folder in current directory

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <meta http-equiv="X-UA-Compatible" content="ie=edge">
    <title>Document</title>
</head>
<body>
    <audio controls>
        <source src="{{ url_for('audio') }}" type="audio/x-wav;codec=pcm">
        Your browser does not support the audio element.
    </audio>
</body>
</html>