How can you convert a Wav file into a PNG waveform image file using Java?
java MyProgram.class [path to wav file] [path where to write png file]
Expected results:
Png saved in path specified is a waveform of the wav file passed in.
Java Program to create a PNG waveform for an audio file
Below is a java class that will do this very thing. There are certain parameters that I'm hard coding here like width of image, height of image, background color of image, and some more stuff. If you want to pull those out, you could.
import java.awt.BasicStroke;
import java.awt.Color;
import java.awt.Font;
import java.awt.Graphics2D;
import java.awt.font.FontRenderContext;
import java.awt.font.LineBreakMeasurer;
import java.awt.font.TextAttribute;
import java.awt.font.TextLayout;
import java.awt.geom.Line2D;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.text.AttributedCharacterIterator;
import java.text.AttributedString;
import java.util.Vector;
import javax.imageio.ImageIO;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.LineUnavailableException;
import javax.sound.sampled.TargetDataLine;
import javax.sound.sampled.UnsupportedAudioFileException;
public class AudioWaveformCreator {
AudioInputStream audioInputStream;
Vector<Line2D.Double> lines = new Vector<Line2D.Double>();
String errStr;
Capture capture = new Capture();
double duration, seconds;
File file;
String fileName;
SamplingGraph samplingGraph;
String waveformFilename;
Color imageBackgroundColor = new Color(20,20,20);
public AudioWaveformCreator(String fileName, String waveformFilename) throws UnsupportedAudioFileException, IOException {
file = new File(fileName);
this.waveformFilename = waveformFilename;
}
public void createAudioInputStream() throws Exception {
if (file != null && file.isFile()) {
try {
errStr = null;
audioInputStream = AudioSystem.getAudioInputStream(file);
fileName = file.getName();
long milliseconds = (long)((audioInputStream.getFrameLength() * 1000) / audioInputStream.getFormat().getFrameRate());
duration = milliseconds / 1000.0;
samplingGraph = new SamplingGraph();
samplingGraph.createWaveForm(null);
} catch (Exception ex) {
reportStatus(ex.toString());
throw ex;
}
} else {
reportStatus("Audio file required.");
}
}
/**
* Render a WaveForm.
*/
class SamplingGraph implements Runnable {
private Thread thread;
private Font font10 = new Font("serif", Font.PLAIN, 10);
private Font font12 = new Font("serif", Font.PLAIN, 12);
Color jfcBlue = new Color(000, 000, 255);
Color pink = new Color(255, 175, 175);
public SamplingGraph() {
}
public void createWaveForm(byte[] audioBytes) {
lines.removeAllElements(); // clear the old vector
AudioFormat format = audioInputStream.getFormat();
if (audioBytes == null) {
try {
audioBytes = new byte[
(int) (audioInputStream.getFrameLength()
* format.getFrameSize())];
audioInputStream.read(audioBytes);
} catch (Exception ex) {
reportStatus(ex.getMessage());
return;
}
}
int w = 500;
int h = 200;
int[] audioData = null;
if (format.getSampleSizeInBits() == 16) {
int nlengthInSamples = audioBytes.length / 2;
audioData = new int[nlengthInSamples];
if (format.isBigEndian()) {
for (int i = 0; i < nlengthInSamples; i++) {
/* First byte is MSB (high order) */
int MSB = (int) audioBytes[2*i];
/* Second byte is LSB (low order) */
int LSB = (int) audioBytes[2*i+1];
audioData[i] = MSB << 8 | (255 & LSB);
}
} else {
for (int i = 0; i < nlengthInSamples; i++) {
/* First byte is LSB (low order) */
int LSB = (int) audioBytes[2*i];
/* Second byte is MSB (high order) */
int MSB = (int) audioBytes[2*i+1];
audioData[i] = MSB << 8 | (255 & LSB);
}
}
} else if (format.getSampleSizeInBits() == 8) {
int nlengthInSamples = audioBytes.length;
audioData = new int[nlengthInSamples];
if (format.getEncoding().toString().startsWith("PCM_SIGN")) {
for (int i = 0; i < audioBytes.length; i++) {
audioData[i] = audioBytes[i];
}
} else {
for (int i = 0; i < audioBytes.length; i++) {
audioData[i] = audioBytes[i] - 128;
}
}
}
int frames_per_pixel = audioBytes.length / format.getFrameSize()/w;
byte my_byte = 0;
double y_last = 0;
int numChannels = format.getChannels();
for (double x = 0; x < w && audioData != null; x++) {
int idx = (int) (frames_per_pixel * numChannels * x);
if (format.getSampleSizeInBits() == 8) {
my_byte = (byte) audioData[idx];
} else {
my_byte = (byte) (128 * audioData[idx] / 32768 );
}
double y_new = (double) (h * (128 - my_byte) / 256);
lines.add(new Line2D.Double(x, y_last, x, y_new));
y_last = y_new;
}
saveToFile(waveformFilename);
}
public void saveToFile(String filename) {
int w = 500;
int h = 200;
int INFOPAD = 15;
BufferedImage bufferedImage = new BufferedImage(w, h, BufferedImage.TYPE_INT_RGB);
Graphics2D g2 = bufferedImage.createGraphics();
createSampleOnGraphicsContext(w, h, INFOPAD, g2);
g2.dispose();
// Write generated image to a file
try {
// Save as PNG
File file = new File(filename);
ImageIO.write(bufferedImage, "png", file);
} catch (IOException e) {
}
}
private void createSampleOnGraphicsContext(int w, int h, int INFOPAD, Graphics2D g2) {
g2.setBackground(imageBackgroundColor);
g2.clearRect(0, 0, w, h);
g2.setColor(Color.white);
g2.fillRect(0, h-INFOPAD, w, INFOPAD);
if (errStr != null) {
g2.setColor(jfcBlue);
g2.setFont(new Font("serif", Font.BOLD, 18));
g2.drawString("ERROR", 5, 20);
AttributedString as = new AttributedString(errStr);
as.addAttribute(TextAttribute.FONT, font12, 0, errStr.length());
AttributedCharacterIterator aci = as.getIterator();
FontRenderContext frc = g2.getFontRenderContext();
LineBreakMeasurer lbm = new LineBreakMeasurer(aci, frc);
float x = 5, y = 25;
lbm.setPosition(0);
while (lbm.getPosition() < errStr.length()) {
TextLayout tl = lbm.nextLayout(w-x-5);
if (!tl.isLeftToRight()) {
x = w - tl.getAdvance();
}
tl.draw(g2, x, y += tl.getAscent());
y += tl.getDescent() + tl.getLeading();
}
} else if (capture.thread != null) {
g2.setColor(Color.black);
g2.setFont(font12);
//g2.drawString("Length: " + String.valueOf(seconds), 3, h-4);
} else {
g2.setColor(Color.black);
g2.setFont(font12);
//g2.drawString("File: " + fileName + " Length: " + String.valueOf(duration) + " Position: " + String.valueOf(seconds), 3, h-4);
if (audioInputStream != null) {
// .. render sampling graph ..
g2.setColor(jfcBlue);
for (int i = 1; i < lines.size(); i++) {
g2.draw((Line2D) lines.get(i));
}
// .. draw current position ..
if (seconds != 0) {
double loc = seconds/duration*w;
g2.setColor(pink);
g2.setStroke(new BasicStroke(3));
g2.draw(new Line2D.Double(loc, 0, loc, h-INFOPAD-2));
}
}
}
}
public void start() {
thread = new Thread(this);
thread.setName("SamplingGraph");
thread.start();
seconds = 0;
}
public void stop() {
if (thread != null) {
thread.interrupt();
}
thread = null;
}
public void run() {
seconds = 0;
while (thread != null) {
if ( (capture.line != null) && (capture.line.isActive()) ) {
long milliseconds = (long)(capture.line.getMicrosecondPosition() / 1000);
seconds = milliseconds / 1000.0;
}
try { thread.sleep(100); } catch (Exception e) { break; }
while ((capture.line != null && !capture.line.isActive()))
{
try { thread.sleep(10); } catch (Exception e) { break; }
}
}
seconds = 0;
}
} // End class SamplingGraph
/**
* Reads data from the input channel and writes to the output stream
*/
class Capture implements Runnable {
TargetDataLine line;
Thread thread;
public void start() {
errStr = null;
thread = new Thread(this);
thread.setName("Capture");
thread.start();
}
public void stop() {
thread = null;
}
private void shutDown(String message) {
if ((errStr = message) != null && thread != null) {
thread = null;
samplingGraph.stop();
System.err.println(errStr);
}
}
public void run() {
duration = 0;
audioInputStream = null;
// define the required attributes for our line,
// and make sure a compatible line is supported.
AudioFormat format = audioInputStream.getFormat();
DataLine.Info info = new DataLine.Info(TargetDataLine.class,
format);
if (!AudioSystem.isLineSupported(info)) {
shutDown("Line matching " + info + " not supported.");
return;
}
// get and open the target data line for capture.
try {
line = (TargetDataLine) AudioSystem.getLine(info);
line.open(format, line.getBufferSize());
} catch (LineUnavailableException ex) {
shutDown("Unable to open the line: " + ex);
return;
} catch (SecurityException ex) {
shutDown(ex.toString());
JavaSound.showInfoDialog();
return;
} catch (Exception ex) {
shutDown(ex.toString());
return;
}
// play back the captured audio data
ByteArrayOutputStream out = new ByteArrayOutputStream();
int frameSizeInBytes = format.getFrameSize();
int bufferLengthInFrames = line.getBufferSize() / 8;
int bufferLengthInBytes = bufferLengthInFrames * frameSizeInBytes;
byte[] data = new byte[bufferLengthInBytes];
int numBytesRead;
line.start();
while (thread != null) {
if((numBytesRead = line.read(data, 0, bufferLengthInBytes)) == -1) {
break;
}
out.write(data, 0, numBytesRead);
}
// we reached the end of the stream. stop and close the line.
line.stop();
line.close();
line = null;
// stop and close the output stream
try {
out.flush();
out.close();
} catch (IOException ex) {
ex.printStackTrace();
}
// load bytes into the audio input stream for playback
byte audioBytes[] = out.toByteArray();
ByteArrayInputStream bais = new ByteArrayInputStream(audioBytes);
audioInputStream = new AudioInputStream(bais, format, audioBytes.length / frameSizeInBytes);
long milliseconds = (long)((audioInputStream.getFrameLength() * 1000) / format.getFrameRate());
duration = milliseconds / 1000.0;
try {
audioInputStream.reset();
} catch (Exception ex) {
ex.printStackTrace();
return;
}
samplingGraph.createWaveForm(audioBytes);
}
} // End class Capture
public static void main(String [] args) throws Exception {
if (args.length != 2) {
printUsage();
System.exit(1);
}
AudioWaveformCreator awc = new AudioWaveformCreator(args[0], args[1]);
awc.createAudioInputStream();
}
private void reportStatus(String msg) {
if ((errStr = msg) != null) {
System.out.println(errStr);
}
}
private static void printUsage() {
System.out.println("AudioWaveformCreator usage: java AudioWaveformCreator.class [path to audio file for generating the image] [path to save waveform image to]");
}
}
Is the green trace supposed to go into the white band at the bottom of the image? What is the purpose of the white band? Note that code is not immediately compilable, and I would recommend rethinking the constructor arguments. –
Zondra
I believe the white band holds some text in case you wanted a label on the waveform. –
Portly
Code totally compiles for me. –
Portly
"Code totally compiles for me" Well you totally have
JavaSound on the class-path for using JavaSound.showInfoDialog();. Strange as it may seem, no one else does. –
Zondra "I believe the white band holds some text in case you wanted a label on the waveform." 1) 'believe'?!? You wrote the code, so what was your intent? 2) I still don't have an answer to the first question, and if that white band is intended for a label, it seems even more strange the wave-form would drop into it. Would you like the image to look at? (And could you answer my 1st question?) –
Zondra
The white BG of SO obscures it, but the image has a 'white band' across the bottom that the blue trace drops into. The sample used for the trace is http://pscode.org/media/leftright.wav which is hot-linked from the SSCCE below.
Code variant
package test.t100.t001;
import java.awt.BasicStroke;
import java.awt.Color;
import java.awt.Font;
import java.awt.Graphics2D;
import java.awt.font.FontRenderContext;
import java.awt.font.LineBreakMeasurer;
import java.awt.font.TextAttribute;
import java.awt.font.TextLayout;
import java.awt.geom.Line2D;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.net.URL;
import java.text.AttributedCharacterIterator;
import java.text.AttributedString;
import java.util.Vector;
import javax.imageio.ImageIO;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.DataLine;
import javax.sound.sampled.LineUnavailableException;
import javax.sound.sampled.TargetDataLine;
import javax.sound.sampled.UnsupportedAudioFileException;
import javax.swing.ImageIcon;
import javax.swing.JLabel;
import javax.swing.JOptionPane;
public class AudioWaveformCreator {
AudioInputStream audioInputStream;
Vector<Line2D.Double> lines = new Vector<Line2D.Double>();
String errStr;
Capture capture = new Capture();
double duration, seconds;
//File file;
String fileName = "out.png";
SamplingGraph samplingGraph;
String waveformFilename;
Color imageBackgroundColor = new Color(20,20,20);
public AudioWaveformCreator(URL url, String waveformFilename) throws Exception {
if (url != null) {
try {
errStr = null;
audioInputStream = AudioSystem.getAudioInputStream(url);
long milliseconds = (long)((audioInputStream.getFrameLength() * 1000) / audioInputStream.getFormat().getFrameRate());
duration = milliseconds / 1000.0;
samplingGraph = new SamplingGraph();
samplingGraph.createWaveForm(null);
} catch (Exception ex) {
reportStatus(ex.toString());
throw ex;
}
} else {
reportStatus("Audio file required.");
}
}
/**
* Render a WaveForm.
*/
class SamplingGraph implements Runnable {
private Thread thread;
private Font font10 = new Font("serif", Font.PLAIN, 10);
private Font font12 = new Font("serif", Font.PLAIN, 12);
Color jfcBlue = new Color(000, 000, 255);
Color pink = new Color(255, 175, 175);
public SamplingGraph() {
}
public void createWaveForm(byte[] audioBytes) {
lines.removeAllElements(); // clear the old vector
AudioFormat format = audioInputStream.getFormat();
if (audioBytes == null) {
try {
audioBytes = new byte[
(int) (audioInputStream.getFrameLength()
* format.getFrameSize())];
audioInputStream.read(audioBytes);
} catch (Exception ex) {
reportStatus(ex.getMessage());
return;
}
}
int w = 500;
int h = 200;
int[] audioData = null;
if (format.getSampleSizeInBits() == 16) {
int nlengthInSamples = audioBytes.length / 2;
audioData = new int[nlengthInSamples];
if (format.isBigEndian()) {
for (int i = 0; i < nlengthInSamples; i++) {
/* First byte is MSB (high order) */
int MSB = (int) audioBytes[2*i];
/* Second byte is LSB (low order) */
int LSB = (int) audioBytes[2*i+1];
audioData[i] = MSB << 8 | (255 & LSB);
}
} else {
for (int i = 0; i < nlengthInSamples; i++) {
/* First byte is LSB (low order) */
int LSB = (int) audioBytes[2*i];
/* Second byte is MSB (high order) */
int MSB = (int) audioBytes[2*i+1];
audioData[i] = MSB << 8 | (255 & LSB);
}
}
} else if (format.getSampleSizeInBits() == 8) {
int nlengthInSamples = audioBytes.length;
audioData = new int[nlengthInSamples];
if (format.getEncoding().toString().startsWith("PCM_SIGN")) {
for (int i = 0; i < audioBytes.length; i++) {
audioData[i] = audioBytes[i];
}
} else {
for (int i = 0; i < audioBytes.length; i++) {
audioData[i] = audioBytes[i] - 128;
}
}
}
int frames_per_pixel = audioBytes.length / format.getFrameSize()/w;
byte my_byte = 0;
double y_last = 0;
int numChannels = format.getChannels();
for (double x = 0; x < w && audioData != null; x++) {
int idx = (int) (frames_per_pixel * numChannels * x);
if (format.getSampleSizeInBits() == 8) {
my_byte = (byte) audioData[idx];
} else {
my_byte = (byte) (128 * audioData[idx] / 32768 );
}
double y_new = (double) (h * (128 - my_byte) / 256);
lines.add(new Line2D.Double(x, y_last, x, y_new));
y_last = y_new;
}
saveToFile();
}
public void saveToFile() {
int w = 500;
int h = 200;
int INFOPAD = 15;
BufferedImage bufferedImage = new BufferedImage(w, h, BufferedImage.TYPE_INT_RGB);
Graphics2D g2 = bufferedImage.createGraphics();
createSampleOnGraphicsContext(w, h, INFOPAD, g2);
g2.dispose();
// Write generated image to a file
try {
// Save as PNG
File file = new File(fileName);
System.out.println(file.getAbsolutePath());
ImageIO.write(bufferedImage, "png", file);
JOptionPane.showMessageDialog(null,
new JLabel(new ImageIcon(fileName)));
} catch (IOException e) {
}
}
private void createSampleOnGraphicsContext(int w, int h, int INFOPAD, Graphics2D g2) {
g2.setBackground(imageBackgroundColor);
g2.clearRect(0, 0, w, h);
g2.setColor(Color.white);
g2.fillRect(0, h-INFOPAD, w, INFOPAD);
if (errStr != null) {
g2.setColor(jfcBlue);
g2.setFont(new Font("serif", Font.BOLD, 18));
g2.drawString("ERROR", 5, 20);
AttributedString as = new AttributedString(errStr);
as.addAttribute(TextAttribute.FONT, font12, 0, errStr.length());
AttributedCharacterIterator aci = as.getIterator();
FontRenderContext frc = g2.getFontRenderContext();
LineBreakMeasurer lbm = new LineBreakMeasurer(aci, frc);
float x = 5, y = 25;
lbm.setPosition(0);
while (lbm.getPosition() < errStr.length()) {
TextLayout tl = lbm.nextLayout(w-x-5);
if (!tl.isLeftToRight()) {
x = w - tl.getAdvance();
}
tl.draw(g2, x, y += tl.getAscent());
y += tl.getDescent() + tl.getLeading();
}
} else if (capture.thread != null) {
g2.setColor(Color.black);
g2.setFont(font12);
//g2.drawString("Length: " + String.valueOf(seconds), 3, h-4);
} else {
g2.setColor(Color.black);
g2.setFont(font12);
//g2.drawString("File: " + fileName + " Length: " + String.valueOf(duration) + " Position: " + String.valueOf(seconds), 3, h-4);
if (audioInputStream != null) {
// .. render sampling graph ..
g2.setColor(jfcBlue);
for (int i = 1; i < lines.size(); i++) {
g2.draw((Line2D) lines.get(i));
}
// .. draw current position ..
if (seconds != 0) {
double loc = seconds/duration*w;
g2.setColor(pink);
g2.setStroke(new BasicStroke(3));
g2.draw(new Line2D.Double(loc, 0, loc, h-INFOPAD-2));
}
}
}
}
public void start() {
thread = new Thread(this);
thread.setName("SamplingGraph");
thread.start();
seconds = 0;
}
public void stop() {
if (thread != null) {
thread.interrupt();
}
thread = null;
}
public void run() {
seconds = 0;
while (thread != null) {
if ( (capture.line != null) && (capture.line.isActive()) ) {
long milliseconds = (long)(capture.line.getMicrosecondPosition() / 1000);
seconds = milliseconds / 1000.0;
}
try { thread.sleep(100); } catch (Exception e) { break; }
while ((capture.line != null && !capture.line.isActive()))
{
try { thread.sleep(10); } catch (Exception e) { break; }
}
}
seconds = 0;
}
} // End class SamplingGraph
/**
* Reads data from the input channel and writes to the output stream
*/
class Capture implements Runnable {
TargetDataLine line;
Thread thread;
public void start() {
errStr = null;
thread = new Thread(this);
thread.setName("Capture");
thread.start();
}
public void stop() {
thread = null;
}
private void shutDown(String message) {
if ((errStr = message) != null && thread != null) {
thread = null;
samplingGraph.stop();
System.err.println(errStr);
}
}
public void run() {
duration = 0;
audioInputStream = null;
// define the required attributes for our line,
// and make sure a compatible line is supported.
AudioFormat format = audioInputStream.getFormat();
DataLine.Info info = new DataLine.Info(TargetDataLine.class,
format);
if (!AudioSystem.isLineSupported(info)) {
shutDown("Line matching " + info + " not supported.");
return;
}
// get and open the target data line for capture.
try {
line = (TargetDataLine) AudioSystem.getLine(info);
line.open(format, line.getBufferSize());
} catch (LineUnavailableException ex) {
shutDown("Unable to open the line: " + ex);
return;
} catch (SecurityException ex) {
shutDown(ex.toString());
//JavaSound.showInfoDialog();
return;
} catch (Exception ex) {
shutDown(ex.toString());
return;
}
// play back the captured audio data
ByteArrayOutputStream out = new ByteArrayOutputStream();
int frameSizeInBytes = format.getFrameSize();
int bufferLengthInFrames = line.getBufferSize() / 8;
int bufferLengthInBytes = bufferLengthInFrames * frameSizeInBytes;
byte[] data = new byte[bufferLengthInBytes];
int numBytesRead;
line.start();
while (thread != null) {
if((numBytesRead = line.read(data, 0, bufferLengthInBytes)) == -1) {
break;
}
out.write(data, 0, numBytesRead);
}
// we reached the end of the stream. stop and close the line.
line.stop();
line.close();
line = null;
// stop and close the output stream
try {
out.flush();
out.close();
} catch (IOException ex) {
ex.printStackTrace();
}
// load bytes into the audio input stream for playback
byte audioBytes[] = out.toByteArray();
ByteArrayInputStream bais = new ByteArrayInputStream(audioBytes);
audioInputStream = new AudioInputStream(bais, format, audioBytes.length / frameSizeInBytes);
long milliseconds = (long)((audioInputStream.getFrameLength() * 1000) / format.getFrameRate());
duration = milliseconds / 1000.0;
try {
audioInputStream.reset();
} catch (Exception ex) {
ex.printStackTrace();
return;
}
samplingGraph.createWaveForm(audioBytes);
}
} // End class Capture
public static void main(String [] args) throws Exception {
//if (args.length != 2) {
// printUsage();
//System.exit(1);
//}
URL url = new URL("http://pscode.org/media/leftright.wav");
AudioWaveformCreator awc = new AudioWaveformCreator(url, "out.png");
}
private void reportStatus(String msg) {
if ((errStr = msg) != null) {
System.out.println(errStr);
}
}
private static void printUsage() {
System.out.println("AudioWaveformCreator usage: java AudioWaveformCreator.class [path to audio file for generating the image] [path to save waveform image to]");
}
}
Hi Andrew. That's strange behavior you are seeing there. I saw a nice healthy waveform on my wavs (which are music files from my band). –
Portly
Does this version of the program you just sent eliminate this issue? –
Portly
Late to the party (apologies, I'm just looking for something similar myself), but setting the INFOBAR variable to 0 will remove the white bar. You've probably already worked that out, but in case anyone else stumbles on this thread :-) –
Ubiety
What happens when
format.getSampleSizeInBits() returns 32 ? I don't understand that piece of code there and why the algorithm is different by changing the sizeInBits from 8 to 16 –
Brinson i'm sure there is a github of someone else doing this better by now –
Portly
ok then here is actual link of such an example: github.com/beschulz/wav2png –
Portly
@NicholasDiPiazza - that example is a C++ application, not Java, which was specifically requested in the question. –
Stith
© 2022 - 2024 — McMap. All rights reserved.