Articles about Alvas.Audio

            string fileName = "test.wav";
            IAudioReader ir = new WaveReader(File.OpenRead(fileName));
            IntPtr format = ir.ReadFormat();
            const int miliseconds = 500;
            int skipBytes = 0;
            // Converts from milliseconds to bytes for current stream.
            int readBytes = ir.Milliseconds2Bytes(miliseconds);
            while (true)
            {
                // Reads audio data starts at skipBytes position and readBytes length.
                byte[] data = ir.ReadDataInBytes(skipBytes, readBytes);
                if (data.Length == 0)
                {
                    break;
                }
                skipBytes += readBytes;
            }
            ir.Close();// Closes the current reader and the underlying stream.

    string inFile = @"c:\work\flac\1.wav";
    Sox.Convert(@"C:\Program Files (x86)\sox-14-4-2\sox.exe", inFile, inFile + ".flac");

        Mp3ToMono(@"d:\down\stereo.mp3");
        WavToMono(@"d:\down\stereo.wav");

        static void Mp3ToMono(string fileName)
        {
            DsReader dr = new DsReader(fileName);
            IntPtr formatPcm = dr.ReadFormat();
            byte[] dataPcm = dr.ReadData();
            dr.Close();
            WaveFormat wfPcm = AudioCompressionManager.GetWaveFormat(formatPcm);
            IntPtr formatPcmMono = AudioCompressionManager.GetPcmFormat(1, wfPcm.wBitsPerSample, wfPcm.nSamplesPerSec);
            var dataPcmMono = AudioCompressionManager.Resample(formatPcm, dataPcm, formatPcmMono);
            var formatMp3Mono = AudioCompressionManager.GetCompatibleFormat(formatPcmMono, AudioCompressionManager.MpegLayer3FormatTag);
            var dataMp3Mono = AudioCompressionManager.Convert(formatPcmMono, formatMp3Mono, dataPcmMono, false);
            using (Mp3Writer mw = new Mp3Writer(File.Create(fileName + ".mp3")))
            {
                mw.WriteData(dataMp3Mono);
            }
        }
        static void WavToMono(string fileName)
        {
            DsReader dr = new DsReader(fileName);
            IntPtr formatPcm = dr.ReadFormat();
            byte[] dataPcm = dr.ReadData();
            dr.Close();
            WaveFormat wfPcm = AudioCompressionManager.GetWaveFormat(formatPcm);
            IntPtr formatPcmMono = AudioCompressionManager.GetPcmFormat(1, wfPcm.wBitsPerSample, wfPcm.nSamplesPerSec);
            var dataPcmMono = AudioCompressionManager.Resample(formatPcm, dataPcm, formatPcmMono);
            using (WaveWriter mw = new WaveWriter(File.Create(fileName + ".wav"), AudioCompressionManager.FormatBytes(formatPcmMono)))
            {
                mw.WriteData(dataPcmMono);
            }
        }

        JoinMp3("out.mp3", "in1.mp3","in2.mp3");
 
        static void JoinMp3(string outFile, params string[] inFiles)
        {
            Mp3Writer mw = new Mp3Writer(File.Create(outFile));
            foreach (string inFile in inFiles)
            {
                Mp3Reader mr = new Mp3Reader(File.OpenRead(inFile));
                mw.WriteData(mr.ReadData());
                mr.Close();
            }
            mw.Close();
        }

Requires Alvas.Audio Trial

	string fileName = @"e:\down\sample.aif";
	AiffReader ar = new AiffReader(File.OpenRead(fileName));
	IntPtr format = ar.ReadFormat();
	byte[] data = ar.ReadData();
	byte[] dataMp3 = AudioCompressionManager.Wave2Mp3(format, data);
	ar.Close();
	var mw = new Mp3Writer(File.Create(fileName + ".mp3"));
	mw.WriteData(dataMp3);
	mw.Close();

Requires Alvas.Audio Trial

        static void OggToWavWithOgg()
        {
            string fileName = @"e:\Down\fortuna.ogg";
            using (DsReader dr = new DsReader(fileName))
            {
                if (dr.HasAudio)
                {
                    short oggFormatTag = 26479;
                    IntPtr format = dr.ReadFormat();
                    WaveFormat waveFormat = AudioCompressionManager.GetWaveFormat(format);
                    IntPtr formatOgg = AudioCompressionManager.GetCompatibleFormat(format, oggFormatTag);
                    using (WaveWriter ww = new WaveWriter(File.Create(fileName + ".wav"),
                        AudioCompressionManager.FormatBytes(formatOgg)))
                    {
                        AudioCompressionManager.Convert(dr, ww, true);
                    }
                }
            }
        }

Requires Alvas.Audio Trial

        static void ToWav()
        {
            string fileName = @"e:\down\male.ogg";
            using (DsReader dr = new DsReader(fileName))
            {
                if (dr.HasAudio)
                {
                    IntPtr format = dr.ReadFormat();
                    using (WaveWriter ww = new WaveWriter(File.Create(fileName + ".wav"),
                        AudioCompressionManager.FormatBytes(format)))
                    {
                        byte[] data = dr.ReadData();
                        ww.WriteData(data);
                    }
                }
            }
        }

Requires Alvas.Audio Trial

    string fileName = @"e:\Down\male.wav";
    Sox.Convert(@"c:\Program Files (x86)\sox-14-4-1\sox.exe", fileName, fileName + ".ogg");

Requires Alvas.Audio Trial

        static void ToWavWithGsm()
        {
            string fileName = @"e:\Down\male.wav";
            WaveReader wr = new WaveReader(File.OpenRead(fileName));
            IntPtr format = wr.ReadFormat();
            IntPtr formatGsm = AudioCompressionManager.GetCompatibleFormat(format,
                AudioCompressionManager.Gsm610FormatTag);
            byte[] dataGsm = AudioCompressionManager.ToFormat(wr, formatGsm);
            WaveWriter ww = new WaveWriter(File.Create(fileName + ".wav"),
                AudioCompressionManager.FormatBytes(formatGsm));
            ww.WriteData(dataGsm);
            ww.Close();
            wr.Close();
        }

Requires Alvas.Audio Trial

    string fileName = @"e:\Down\test.wmv";
    DsConvert.ToWma(fileName, fileName + ".wma", DsConvert.WmaProfile.Stereo128);

Requires Alvas.Audio Trial

    Private plex As PlayerEx = New PlayerEx()

    Sub Play2Seconds(ByVal fileName As String)
        Dim dr As DsReader = New DsReader(fileName)
        Dim format As IntPtr = dr.ReadFormat()
        Dim data As Byte() = dr.ReadData(0, 2)
        dr.Close()
        plex.OpenPlayer(format)
        plex.AddData(data)
        plex.StartPlay()
    End Sub

Requires Alvas.Audio Trial

        static void ToPcm8khzMono16bit65kB(string fileName)
        {
            const int maxSize = 65*1024 - 44/*Wav specific size*/;
            DsReader dr = new DsReader(fileName);
            //PCM 8khz mono 16bit
            IntPtr format = AudioCompressionManager.GetPcmFormat(1, 16, 8000);
            byte[] data = AudioCompressionManager.ToFormat(dr, format);
            dr.Close();
            //Cut the audio file to max size
            if (data.Length > maxSize)
            {
                WaveFormat wf = AudioCompressionManager.GetWaveFormat(format);
                int align = wf.nBlockAlign;
                int size = maxSize / align * align;
                byte[] data2 = new byte[size];
                Buffer.BlockCopy(data, 0, data2, 0, size);
                data = data2;
            }
            WaveWriter ww = new WaveWriter(File.Create(fileName + ".wav"), 
                AudioCompressionManager.FormatBytes(format));
            ww.WriteData(data);
            ww.Close();
        }

Requires Alvas.Audio Trial

static void AnyToWav(string fileName)
{
    DsReader dr1 = new DsReader(fileName);
    if (dr1.HasAudio)
    {
        WaveWriter ww = new WaveWriter(File.Create(fileName + ".wav"), 
           AudioCompressionManager.FormatBytes(dr1.ReadFormat()));
        ww.WriteData(dr1.ReadData());
        ww.Close();
        Console.WriteLine("Done!");
    }
    else
    {
        Console.WriteLine("Has no audio");
    }
}

Project\Properties\Build\Platform Target: x86

Requires Alvas.Audio Trial

Project\Properties\Build\Platform Target: x86

Control Panel\Administrative Tools\Internet Information Services (IIS) Manager\.
    .\Application Pools\{your pool}\Advanced Settings..\Enable 32-Bit Applications: True

Start Automatically: True

Requires Alvas.Audio Trial

    class Program
    {
        static PlayerEx pl = new PlayerEx(true);

        static void ConsolePlayer(string fileName)
        {
            pl.Done += new PlayerEx.DoneEventHandler(pl_Done);
            WaveReader wr = new WaveReader(File.OpenRead(fileName));
            pl.OpenPlayer(wr.ReadFormat());
            pl.AddData(wr.ReadData());
            pl.StartPlay();
            System.Threading.Thread.CurrentThread.Join();
        }

        static void pl_Done(object sender, DoneEventArgs e)
        {
            if (e.IsEndPlaying)
            {
                System.Threading.Thread.CurrentThread.Abort();
            }
        }

        static void Main()
        {
            ConsolePlayer(@"e:\Down\1\1.wav");
        }
    }

Requires Alvas.Audio Trial

        // Multiple encoding Wav PCM -> Mp3 
        private static void MultipleWav2Mp3()
        {
            var path = "e:\\Down\\wav\\";
            var files = new List() { "notify.wav", "tada.wav", "chimes.wav" };
            Parallel.ForEach(files, file =>
            {
                AudioCompressionManager.Wave2Mp3(path + file, path + file + ".mp3");
            });
        }

        // Multiple decoding any audio file -> Wav PCM
        private static void MultipleAny2Pcm()
        {
            var path = "e:\\Down\\wav\\";
            var files = new List() { "1.wma", "2.m4a", "3.aif" };
            Parallel.ForEach(files, file =>
            {
                using (var dr = new DsReader(path + file))
                {
                    using (var ww = new WaveWriter(File.Create(path + file + ".wav"),
                        AudioCompressionManager.FormatBytes(dr.ReadFormat())))
                    {
                        ww.WriteData(dr.ReadData());
                    }
                }
            });
        }

Requires .Net framework 4.0 and Alvas.Audio Trial

Question: How to use RecorderEx and PlayerEx in console application or Windows Service?

Answer: In order to use RecorderEx and PlayerEx in a console application or Windows Service need to create instances of these classes by using a parameterized constructor:
new RecorderEx(true) and new PlayerEx(true), respectively. The same is true for multi-threaded recorder and player.

Below is an example of full duplex Recorder and Player.

Below is an example of multithreaded full duplex Recorder and Player in Windows Service.

Question: I found that your vox converter doesn't handle vox files from the Orator phone dictation system right.

Answer: There are so many questions about Vox format. What is the Vox format? Vox audio file format is a headerless audio format data, which generally contains Dialogic_ADPCM, but may also include A-law, Mu-law, PCM, and any other type of audio data.
It means that vox file doesn't have the header and extention ".vox" doesn't say anything at all. Therefore it is very important to know in which format you have the audio data in the vox file!

See code below for the different types of Vox files.

DC offset is an offsetting of a signal from zero. It occurs when hardware, such as a sound card, adds DC offset to the recorded audio signal.
DC offset is shift of the red line comparatively to the black one on figure below.

To remove the DC offset is used AudioCompressionManager.RemoveDcOffset method. See code below

Question: Have you got any issues with "Joint-Stereo" MP3's? I have a customer who sends me the attached MP3 and when I convert it to a mono format, it effectively cancels out the audio.

Answer: The problem is that in Mp3 Joint Stereo sound file mirror is opposite. For example the left channel = -1, and the right channel = +1. When converting a file into single channels are merged: -1 + 1 = 0. So you hear the silence. You can solve this problem in that way. Instead of combining the channels keep only one channel (left or right).

The code below solves this problem.

Very often we have to change the sampling rate, number of channels and the size of a sample when converting from one format to another. You can use AudioCompressionManager.Convert method for these purposes. Unfortunately, for the uncompressed PCM -> PCM this leads to a significant reduction in sound quality and appearance of extraneous noise. We can verify this by example.

Fortunately, Alvas.Audio library has AudioCompressionManager.Resample method. It is a wrapper over Resampler DMO object. If we rewrite the code above using AudioCompressionManager.Resample method, we get much better sound quality.

You can compare the sound of these 3 files.

• Original.WAV
• Original.WAV.Convert.Wav
• GLASS.WAV.Resample.Wav

As a bonus AudioCompressionManager.Resample method can encode and decode the PCM 24 and 32 bit, more than 2 channels, and also 32-bit IEEE Float audio format.

Summary: For encode and decode a compressed format to PCM AudioCompressionManager.Convert fits perfectly, but for resampling use AudioCompressionManager.Resample method.

• Audio Readers is a hierarchy of Alvas.Audio classes that implement IAudioReader interface used to read format and audio data.
• AudioReader is a base class for the readers that can read an audio data from the stream. This class is abstract.
  • AuReader class reads an audio data from the .AU and .SND streams.
  • AviReader class reads audio data from the Avi stream.
  • WaveReader class reads WAVE (waveform audio format) data from the stream.
  • RawReader class reads an audio data from the headerless stream. Slinear, Gsm, A-law, mu-law etc. For that, you need to specify explicitly the format of the audio data that they contain.
  • Mp3Reader class reads audio data from the Mp3 stream.
• DsReader class reads audio data using DirectShow. List of supported formats can be expanded with additional DirectShow filters installed.
  Use X Codec Pack to expand the list of supported formats. At the moment, can only work with files stored on disk.

Three methods of IAudioReader interface most commonly used.

To read the audio data portions of 1 second, you can use the following code.

To read the audio data by portions that are smaller than 1 second, you can use the following code.

The following code allows to determine the audio stream duration in milliseconds and the audio data size in bytes.

Avi files are video files. They may not contain audio data. To determine this AviReader class has HasAudio property. DsReader HasAudio equal false means that the file contains no audio data or audio file format is unknown, ie no suitable DirectShow filter.

Audio file formats can be with a header, without header and with header in each packet of audio data.

• Wav file is a classic audio format with a header. It is also called container format, because it may contain an audio data in a different format, which is specified in the header.
• Headerless(Raw audio format) audio files can contain only audio data. Therefore, we must know exactly the format of the audio data. These files usually have .raw, .sln, .pcm, .alaw, .ulaw, .gsm and other file extensions.
• MP3 format contains a header in each packet of audio data. Therefore, this format is suitable for broadcasting audio over the network.

1. Upload audio file.
2. Select your audio file from list on the server.
3. Select audio format from list with available audio formats.
4. Press “Convert” button and download result audio file.

You can see online demo and example code and Alvas.Audio and X Codec Pack.

1. To create RecorderEx or PlayerEx use a constructor with a parameter isConsole = true. Example: new RecorderEx (true); or PlayerEx (true);
2. Add reference to WindowsFormsIntegration assembly (in WindowsFormsIntegration.dll) to your project.
3. Add reference to System.Windows.Forms assembly (in System.Windows.Forms.dll) to your project.
4. In the Window element, add the following namespace mapping

   xmlns:wf="clr-namespace:System.Windows.Forms;assembly=System.Windows.Forms"

   in Window1.xaml. The wf namespace mapping establishes a reference to the assembly that contains the Windows Forms control.
5. Place WindowsFormsHost container with our control. For example, PropertyGrid

   <WindowsFormsHost Grid.Row="1" Grid.Column="0" >

       <wf:PropertyGrid x:Name="pgMain"/>

   </WindowsFormsHost>

6. You can add control into WindowsFormsHost container in run-time:
1. Place empty WindowsFormsHost container to our Window1.xaml

   <WindowsFormsHost Name="wfh" Grid.Row="1" Grid.Column="1" ></WindowsFormsHost>

2. and create WaveformVisualizer (from Alvas.Audio.dll) control and place it to WindowsFormsHost container in run-time

   private void InitWaveformVisualizer()

   {

       wfv = new WaveformVisualizer();

       wfh.Child = wfv;

   }

   private WaveformVisualizer wfv;

1. Make the COM object wrapper, which allows us to invoke the necessary Alvas.Audio functionality.
   1. Create AlvasCom project as ClassLibrary.
   2. In AssemblyInfo.cs change the line

      [assembly: ComVisible(false)]

      to

      [assembly: ComVisible(true)]

   3. Add a reference to Alvas.Audio.dll
   4. Add Alvas.Audio-wrapper interface and its implementation. See the code below.

      namespace AlvasCom

      {

          [Guid("50B29476-F2C0-4445-B0E1-7D4023453EBD")]

          interface IAudioHost

          {

              void Close();

              void WriteData(short channels, short bitsPerSample, int samplesPerSec, byte[] sampleData);

          }

          [ClassInterface(ClassInterfaceType.None)]

          [Guid("1EA86BAE-420F-4309-BF06-23730718BF5E")]

          public class AudioHost : IAudioHost

          {

              Mp3Writer mw;

              public AudioHost()

              {

                  string dir = Environment.GetFolderPath(Environment.SpecialFolder.MyMusic);

                  string fileName = Path.ChangeExtension(Path.GetFileName(Path.GetTempFileName()), ".mp3");

                  string path = Path.Combine(dir, fileName);

                  global::System.Windows.Forms.MessageBox.Show(path);

                  mw = new Mp3Writer(File.Create(path));

              }

              public void WriteData(short channels, short bitsPerSample, int samplesPerSec,

                  byte[] sampleData)

              {

                  IntPtr sampleFormat = AudioCompressionManager.GetPcmFormat(channels, bitsPerSample,

                      samplesPerSec);

                  IntPtr format = AudioCompressionManager.GetCompatibleFormat(sampleFormat,

                      AudioCompressionManager.MpegLayer3FormatTag);

                  byte[] data = AudioCompressionManager.Convert(sampleFormat, format, sampleData, false);

                  mw.WriteData(data);

              }

              public void Close()

              {

                  mw.Close();

              }

          }

      }

   5. Sign the assembly with the snk file.
   6. Register in GAC AlvasCom.dll and Alvas.Audio.dll using gacutil.
   7. Register the COM object using regasm.
   
   You can find AlvasCom.bat in the "SilverlightAudio\AlvasCom\bin\Debug\" folder to register these libraries.
   
   
2. Make the Silverlight application with microphone support.
   1. Create SilverlightAudio project as SilverlightApplication.
   2. To call a COM object, we need elevated privileges and run it out of browser. Add to OutOfBrowserSettings.xml

        <OutOfBrowserSettings.SecuritySettings>
          <SecuritySettings ElevatedPermissions="Required" />
        </OutOfBrowserSettings.SecuritySettings>

   3. Writing code call using the "dynamic" type

      namespace SilverlightAudio

      {

          public class MyAudioSync : AudioSink

          {

              dynamic ah;

              AudioFormat audioFormat;

              protected override void OnCaptureStarted()

              {

                  ah = AutomationFactory.CreateObject("AlvasCom.AudioHost");

              }

              protected override void OnCaptureStopped()

              {

                  ah.Close();

              }

              protected override void OnFormatChange(AudioFormat audioFormat)

              {

                  this.audioFormat = audioFormat;

              }

              protected override void OnSamples(long sampleTime, long sampleDuration, byte[] sampleData)

              {

                  ah.WriteData((short)audioFormat.Channels, (short)audioFormat.BitsPerSample,

                      audioFormat.SamplesPerSecond, sampleData);

              }

          }

      }

   4. Compile and run the application.
   5. Enjoy.

1. Save mp3 file on the server.
2. Make voice chat, but it is better to use gsm instead of mp3 encoding. How to do it - leave it in the form of homework. Hint #tip60 :)
3. And what can you propose?

# # #
Driver: Microsoft GSM 6.10 Audio CODEC
FormatTag: GSM 6.10
Format: 8,000 kHz; Mono
Format: 11,025 kHz; Mono
Format: 22,050 kHz; Mono
Format: 44,100 kHz; Mono
FormatTag: PCM
Format: 8,000 kHz; 8 Bit; Mono
Format: 8,000 kHz; 16 Bit; Mono
Format: 11,025 kHz; 8 Bit; Mono
Format: 11,025 kHz; 16 Bit; Mono
Format: 22,050 kHz; 8 Bit; Mono
Format: 22,050 kHz; 16 Bit; Mono
Format: 44,100 kHz; 8 Bit; Mono
Format: 44,100 kHz; 16 Bit; Mono
# # #

• FormatTag = 1 is PCM.
• Channels = for single-channel (mono), two-channel (stereo), 8 for 7.1 Surround Sound (left, right, center, left surround, right surround, left rear, right rear positions. 7.1 systems also have 1 channel for low frequency effects (LFE) which is usually sent to a subwoofer).
• SamplesPerSec = digitized quantity values per second (or sampling). Could be anything, but the standard values: 8000 Hz, 11025 Hz, 12000 Hz, 16000 Hz, 22050 Hz, 24000 Hz, 32000 Hz, 44100 Hz, 48000 Hz.
• BitsPerSample - most common uses 8 bits (1 byte) and 16 bits (2 bytes). Rarely 24 bits (3 bytes), 32 bits (4 bytes) and 64 bits (4 bytes). If we consider the 16 bit as a basic, then 8 bits can be considered as a compressed format. It has two times less size, but the variants of values can be only 2⁸ = 256 instead of 2¹⁶ = 65536 for 16 bits. That's why, 8 bits sound quality will be significantly lower than 16 bits.
• BlockAlign = Channels * BitsPerSample / 8. Where 8 is the quantity of bits per byte.
• AvgBytesPerSec (bitrate) = Channels * SamplesPerSec * BitsPerSample / 8.