I am developing one app in which I need to pass through audio capturing through output audio jack at the same time record and save video.
I have looked into aurio touch apple sample code and implemented audio passthrough.
I have also implemented the video recording through AVCaptureSession.
Above both functionality individually done and works pefectly.
But when I merge functionality audio pass through not working because of audio session of the AVCapturesession.
I have also tried to pass through audio data which I am getting from AVCaptureSession delegate methods. Below is my code :
OSStatus err = noErr;
AudioBufferList audioBufferList;
CMBlockBufferRef blockBuffer;
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(sampleBuffer, NULL, &audioBufferList, sizeof(audioBufferList), NULL, NULL, 0, &blockBuffer);
CMItemCount numberOfFrames = CMSampleBufferGetNumSamples(sampleBuffer); // corresponds to the number of CoreAudio audio frames
currentSampleTime += (double)numberOfFrames;
AudioTimeStamp timeStamp;
memset(&timeStamp, 0, sizeof(AudioTimeStamp));
timeStamp.mSampleTime = currentSampleTime;
timeStamp.mFlags |= kAudioTimeStampSampleTimeValid;
AudioUnitRenderActionFlags flags = 0;
aurioTouchAppDelegate *THIS = (aurioTouchAppDelegate *)[[UIApplication sharedApplication]delegate];
err = AudioUnitRender(self.rioUnit, &flags, &timeStamp, 1, numberOfFrames, &audioBufferList);
if (err) { printf("PerformThru: error %d\n", (int)err); }
But it is giving error. Please advise what can be done further as soon as possible. I have looked into so many docs and so many codes but couldn't find any solution. Please help..
Here's some better error handling code. What error does it return? You can look up the error description by searching for it in the documentation.
static void CheckError (OSStatus error, const char *operation) {
if (error == noErr) return;
char str[20] = {};
// see if it appears to be a 4 char code
*(UInt32*)(str + 1) = CFSwapInt32HostToBig(error);
if (isprint(str[1]) && isprint(str[2]) && isprint(str[3]) && isprint(str[4])) {
str[0] = str[5] = '\'';
str[6] = '\0';
} else {
sprintf(str, "%d", (int)error);
}
fprintf(stderr, "Error: %s(%s)\n", operation, str);
exit(1);
}
- (void)yourFunction
{
AudioBufferList audioBufferList;
CMBlockBufferRef blockBuffer;
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(sampleBuffer, NULL, &audioBufferList, sizeof(audioBufferList), NULL, NULL, 0, &blockBuffer);
CMItemCount numberOfFrames = CMSampleBufferGetNumSamples(sampleBuffer); // corresponds to the number of CoreAudio audio frames
currentSampleTime += (double)numberOfFrames;
AudioTimeStamp timeStamp;
memset(&timeStamp, 0, sizeof(AudioTimeStamp));
timeStamp.mSampleTime = currentSampleTime;
timeStamp.mFlags |= kAudioTimeStampSampleTimeValid;
AudioUnitRenderActionFlags flags = 0;
aurioTouchAppDelegate *THIS = (aurioTouchAppDelegate *)[[UIApplication sharedApplication]delegate];
CheckError(AudioUnitRender(self.rioUnit, &flags, &timeStamp, 1, numberOfFrames, &audioBufferList),
"Error with AudioUnitRender");
}
Related
I have an IPCamera that requires the use of a custom library for connecting and communication. I have the video all taken care of, but I also want to give the user the option to listen to the audio that is recorded by the camera.
I receive the audio in the form of a byte stream (the audio is PCM u-law).
Since I don't read the data from a file or have an URL I can connect to, I think I would have to use something like AudioUnits or openAL to play my audio.
I tried to implement it with AudioUnits based on the examples I found online and this is what I have so far:
-(void) audioThread
{
char buffer[1024];
int size = 0;
boolean audioConfigured = false;
AudioComponentInstance audioUnit;
while (running) {
getAudioData(buffer,size); //fill buffer with my audio
int16_t* tempChar = (int16_t *)calloc(ret, sizeof(int16_t));
for (int i = 0; i < ret; i++) {
tempChar[i] = MuLaw_Decode(buf[i]);
}
uint8_t *data = NULL;
data = malloc(size);
data = memcpy(data, &tempChar, size);
CMBlockBufferRef blockBuffer = NULL;
OSStatus status = CMBlockBufferCreateWithMemoryBlock(NULL, data,
size,
kCFAllocatorNull, NULL,
0,
size,
0, &blockBuffer);
CMSampleBufferRef sampleBuffer = NULL;
// now I create my samplebuffer from the block buffer
if(status == noErr)
{
const size_t sampleSize = size;
status = CMSampleBufferCreate(kCFAllocatorDefault,
blockBuffer, true, NULL, NULL,
formatDesc, 1, 0, NULL, 1,
&sampleSize, &sampleBuffer);
}
AudioStreamBasicDescription audioBasic;
audioBasic.mBitsPerChannel = 16;
audioBasic.mBytesPerPacket = 2;
audioBasic.mBytesPerFrame = 2;
audioBasic.mChannelsPerFrame = 1;
audioBasic.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked;
audioBasic.mFormatID = kAudioFormatLinearPCM;
audioBasic.mFramesPerPacket = 1;
audioBasic.mSampleRate = 48000;
audioBasic.mReserved = 0;
if(!audioConfigured)
{
//initialize the circular buffer
if(instance.decodingBuffer == NULL)
instance.decodingBuffer = malloc(sizeof(TPCircularBuffer));
if(!TPCircularBufferInit(instance.decodingBuffer, 1024))
continue;
AudioComponentDescription componentDescription;
componentDescription.componentType = kAudioUnitType_Output;
componentDescription.componentSubType = kAudioUnitSubType_RemoteIO;
componentDescription.componentManufacturer = kAudioUnitManufacturer_Apple;
componentDescription.componentFlags = 0;
componentDescription.componentFlagsMask = 0;
AudioComponent component = AudioComponentFindNext(NULL, &componentDescription);
if(AudioComponentInstanceNew(component, &audioUnit) != noErr) {
NSLog(#"Failed to initialize the AudioComponent");
continue;
}
//enable IO for playback
UInt32 flag = 1;
if(AudioUnitSetProperty(audioUnit, kAudioOutputUnitProperty_EnableIO, kAudioUnitScope_Output, 0, &flag, sizeof(flag)) != noErr) {
NSLog(#"Failed to enable IO for playback");
continue;
}
// set the format for the outputstream
if(AudioUnitSetProperty(audioUnit, kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Output, 1, &audioBasic, sizeof(audioBasic)) != noErr) {
NSLog(#"Failed to set the format for the outputstream");
continue;
}
// set output callback
AURenderCallbackStruct callbackStruct;
callbackStruct.inputProc = playbackCallback;
callbackStruct.inputProcRefCon = (__bridge void*) self;
if(AudioUnitSetProperty(audioUnit, kAudioUnitProperty_SetRenderCallback, kAudioUnitScope_Global, 0, &callbackStruct, sizeof(callbackStruct))!= noErr) {
NSLog(#"Failed to Set output callback");
continue;
}
// Disable buffer allocation for the recorder (optional - do this if we want to pass in our own)
flag = 0;
status = AudioUnitSetProperty(audioUnit, kAudioUnitProperty_ShouldAllocateBuffer, kAudioUnitScope_Output, 1, &flag, sizeof(flag));
if(AudioUnitInitialize(audioUnit) != noErr) {
NSLog(#"Failed to initialize audioUnits");
}
if(AudioOutputUnitStart(audioUnit)!= noErr) {
NSLog(#"[thread_ReceiveAudio] Failed to start audio");
}
audioConfigured = true;
}
AudioBufferList bufferList ;
if (sampleBuffer!=NULL) {
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(sampleBuffer, NULL, &bufferList, sizeof(bufferList), NULL, NULL, kCMSampleBufferFlag_AudioBufferList_Assure16ByteAlignment, &blockBuffer);
UInt64 size = CMSampleBufferGetTotalSampleSize(sampleBuffer);
// Put audio into circular buffer
TPCircularBufferProduceBytes(self.decodingBuffer, bufferList.mBuffers[0].mData, size);
//TPCircularBufferCopyAudioBufferList(self.decodingBuffer, &bufferList, NULL, kTPCircularBufferCopyAll, NULL);
CFRelease(sampleBuffer);
CFRelease(blockBuffer);
}
}
//stop playing audio
if(audioConfigured){
if(AudioOutputUnitStop(audioUnit)!= noErr) {
NSLog(#"[thread_ReceiveAudio] Failed to stop audio");
}
else{
//clean up audio
AudioComponentInstanceDispose(audioUnit);
}
}
}
int16_t MuLaw_Decode(int8_t number)
{
const uint16_t MULAW_BIAS = 33;
uint8_t sign = 0, position = 0;
int16_t decoded = 0;
number = ~number;
if (number & 0x80)
{
number &= ~(1 << 7);
sign = -1;
}
position = ((number & 0xF0) >> 4) + 5;
decoded = ((1 << position) | ((number & 0x0F) << (position - 4))
| (1 << (position - 5))) - MULAW_BIAS;
return (sign == 0) ? (decoded) : (-(decoded));
}
static OSStatus playbackCallback(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData) {
int bytesToCopy = ioData->mBuffers[0].mDataByteSize;
SInt16 *targetBuffer = (SInt16*)ioData->mBuffers[0].mData;
int32_t availableBytes;
SInt16 *buffer = TPCircularBufferTail(instance.decodingBuffer, &availableBytes);
int sampleCount = MIN(bytesToCopy, availableBytes);
memcpy(targetBuffer, buffer, MIN(bytesToCopy, availableBytes));
TPCircularBufferConsume(self.decodingBuffer, sampleCount);
return noErr;
}
The code above doesn't produce any errors, but won't play any sound. I though I could set the audio through the bufferList in the recordCallback, but it is never called.
So my question is: How do I play audio from a byte stream on iOS?
I decided to look at the project with fresh eyes. I got rid of most of the code and got it to work now. It is not pretty, but at least it runs for now. For example: I had to set my sample rate to 4000, otherwise it would play to fast and I still have performance issues. Anyway this is what I came up with:
#define BUFFER_SIZE 1024
#define NUM_CHANNELS 2
#define kOutputBus 0
#define kInputBus 1
-(void) main
{
char buf[BUFFER_SIZE];
int size;
runloop: while (self.running) {
getAudioData(&buf, size);
if(!self.configured) {
if(![self activateAudioSession])
continue;
self.configured = true;
}
TPCircularBufferProduceBytes(self.decodingBuffer, buf, size);
}
//stop audiounits
AudioOutputUnitStop(self.audioUnit);
AudioComponentInstanceDispose(self.audioUnit);
if (self.decodingBuffer != NULL) {
TPCircularBufferCleanup(self.decodingBuffer);
}
}
static void audioSessionInterruptionCallback(void *inUserData, UInt32 interruptionState) {
if (interruptionState == kAudioSessionEndInterruption) {
AudioSessionSetActive(YES);
AudioOutputUnitStart(self.audioUnit);
}
if (interruptionState == kAudioSessionBeginInterruption) {
AudioOutputUnitStop(self.audioUnit);
}
}
static OSStatus playbackCallback(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData) {
// Notes: ioData contains buffers (may be more than one!)
// Fill them up as much as you can. Remember to set the size value in each buffer to match how much data is in the buffer.
if (!self.running ) {
return -1;
}
int bytesToCopy = ioData->mBuffers[0].mDataByteSize;
SInt16 *targetBuffer = (SInt16*)ioData->mBuffers[0].mData;
// Pull audio from playthrough buffer
int32_t availableBytes;
if(self.decodingBuffer == NULL || self.decodingBuffer->length < 1) {
NSLog(#"buffer is empty");
return 0;
}
SInt16 *buffer = TPCircularBufferTail(self.decodingBuffer, &availableBytes);
int sampleCount = MIN(bytesToCopy, availableBytes);
memcpy(targetBuffer, buffer, sampleCount);
TPCircularBufferConsume(self.decodingBuffer, sampleCount);
return noErr;
}
- (BOOL) activateAudioSession {
if (!self.activated_) {
OSStatus result;
result = AudioSessionInitialize(NULL,
NULL,
audioSessionInterruptionCallback,
(__bridge void *)(self));
if (kAudioSessionAlreadyInitialized != result)
[self checkError:result message:#"Couldn't initialize audio session"];
[self setupAudio]
self.activated_ = YES;
}
return self.activated_;
}
- (void) setupAudio
{
OSStatus status;
// Describe audio component
AudioComponentDescription desc;
desc.componentType = kAudioUnitType_Output;
desc.componentSubType = kAudioUnitSubType_RemoteIO;
desc.componentFlags = 0;
desc.componentFlagsMask = 0;
desc.componentManufacturer = kAudioUnitManufacturer_Apple;
// Get component
AudioComponent inputComponent = AudioComponentFindNext(NULL, &desc);
// Get audio units
AudioComponentInstanceNew(inputComponent, &_audioUnit);
// // Enable IO for recording
// UInt32 flag = 1;
// status = AudioUnitSetProperty(audioUnit,
// kAudioOutputUnitProperty_EnableIO,
// kAudioUnitScope_Input,
// kInputBus,
// &flag,
// sizeof(flag));
// Enable IO for playback
UInt32 flag = 1;
AudioUnitSetProperty(_audioUnit,
kAudioOutputUnitProperty_EnableIO,
kAudioUnitScope_Output,
kOutputBus,
&flag,
sizeof(flag));
// Describe format
AudioStreamBasicDescription format;
format.mSampleRate = 4000;
format.mFormatID = kAudioFormatULaw; //kAudioFormatULaw
format.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked;//
format.mBitsPerChannel = 8 * sizeof(char);
format.mChannelsPerFrame = NUM_CHANNELS;
format.mBytesPerFrame = sizeof(char) * NUM_CHANNELS;
format.mFramesPerPacket = 1;
format.mBytesPerPacket = format.mBytesPerFrame * format.mFramesPerPacket;
format.mReserved = 0;
self.audioFormat = format;
// Apply format
AudioUnitSetProperty(_audioUnit,
kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Output,
kInputBus,
&_audioFormat,
sizeof(_audioFormat));
AudioUnitSetProperty(_audioUnit,
kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Input,
kOutputBus,
&_audioFormat,
sizeof(_audioFormat));
// // Set input callback
// AURenderCallbackStruct callbackStruct;
// callbackStruct.inputProc = recordingCallback;
// callbackStruct.inputProcRefCon = self;
// status = AudioUnitSetProperty(audioUnit,
// kAudioOutputUnitProperty_SetInputCallback,
// kAudioUnitScope_Global,
// kInputBus,
// &callbackStruct,
// sizeof(callbackStruct));
// checkStatus(status);
// Set output callback
AURenderCallbackStruct callbackStruct;
callbackStruct.inputProc = playbackCallback;
callbackStruct.inputProcRefCon = (__bridge void * _Nullable)(self);
AudioUnitSetProperty(_audioUnit,
kAudioUnitProperty_SetRenderCallback,
kAudioUnitScope_Global,
kOutputBus,
&callbackStruct,
sizeof(callbackStruct));
// Disable buffer allocation for the recorder (optional - do this if we want to pass in our own)
flag = 0;
status = AudioUnitSetProperty(_audioUnit,
kAudioUnitProperty_ShouldAllocateBuffer,
kAudioUnitScope_Output,
kInputBus,
&flag,
sizeof(flag));
//initialize the circular buffer
if(self.decodingBuffer == NULL)
self.decodingBuffer = malloc(sizeof(TPCircularBuffer));
if(!TPCircularBufferInit(self.decodingBuffer, 512*1024))
return NO;
// Initialise
status = AudioUnitInitialize(self.audioUnit);
AudioOutputUnitStart(self.audioUnit);
}
I found most of this by looking through github and from a tasty pixel
If the AVAudioSession is configured to use short buffers, you can use the RemoteIO Audio Unit to play received audio with low additional latency.
Check errors during audio configuration. Some iOS devices only support a 48 kHz sample rate, so you may need to resample your audio PCM data from 8 kHz to another rate.
RemoteIO only supports linear PCM, so you will need to first convert all your incoming 8-bit u-law PCM samples to 16-bit linear PCM format before storing them in a lock-free circular buffer.
You need to call AudioOutputUnitStart to start audio callbacks being called by the OS. Your code should not be calling these callbacks. They will be called by the OS.
AudioUnitRender is used for recording callbacks, not for playing audio. So you don't need to use it. Just fill the AudioBufferList buffers with the requested number of frames in the play callback.
Then you can use the play audio callback to check your circular buffer and pull the requested number of samples, if enough are available. You should not do any memory management (such as a free() call) inside this callback.
I am trying to take a video file read it in using AVAssetReader and pass the audio off to CoreAudio for processing (adding effects and stuff) before saving it back out to disk using AVAssetWriter. I would like to point out that if i set the componentSubType on AudioComponentDescription of my output node as RemoteIO, things play correctly though the speakers. This makes me confident that my AUGraph is properly setup as I can hear things working. I am setting the subType to GenericOutput though so I can do the rendering myself and get back the adjusted audio.
I am reading in the audio and i pass the CMSampleBufferRef off to copyBuffer. This puts the audio into a circular buffer that will be read in later.
- (void)copyBuffer:(CMSampleBufferRef)buf {
if (_readyForMoreBytes == NO)
{
return;
}
AudioBufferList abl;
CMBlockBufferRef blockBuffer;
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(buf, NULL, &abl, sizeof(abl), NULL, NULL, kCMSampleBufferFlag_AudioBufferList_Assure16ByteAlignment, &blockBuffer);
UInt32 size = (unsigned int)CMSampleBufferGetTotalSampleSize(buf);
BOOL bytesCopied = TPCircularBufferProduceBytes(&circularBuffer, abl.mBuffers[0].mData, size);
if (!bytesCopied){
/
_readyForMoreBytes = NO;
if (size > kRescueBufferSize){
NSLog(#"Unable to allocate enought space for rescue buffer, dropping audio frame");
} else {
if (rescueBuffer == nil) {
rescueBuffer = malloc(kRescueBufferSize);
}
rescueBufferSize = size;
memcpy(rescueBuffer, abl.mBuffers[0].mData, size);
}
}
CFRelease(blockBuffer);
if (!self.hasBuffer && bytesCopied > 0)
{
self.hasBuffer = YES;
}
}
Next I call processOutput. This will do a manual reder on the outputUnit. When AudioUnitRender is called it invokes the playbackCallback below, which is what is hooked up as input callback on my first node. playbackCallback pulls the data off the circular buffer and feeds it into the audioBufferList passed in. Like I said before if the output is set as RemoteIO this will cause the audio to correctly be played on the speakers. When AudioUnitRender finishes, it returns noErr and the bufferList object contains valid data. When I call CMSampleBufferSetDataBufferFromAudioBufferList though I get kCMSampleBufferError_RequiredParameterMissing (-12731).
-(CMSampleBufferRef)processOutput
{
if(self.offline == NO)
{
return NULL;
}
AudioUnitRenderActionFlags flags = 0;
AudioTimeStamp inTimeStamp;
memset(&inTimeStamp, 0, sizeof(AudioTimeStamp));
inTimeStamp.mFlags = kAudioTimeStampSampleTimeValid;
UInt32 busNumber = 0;
UInt32 numberFrames = 512;
inTimeStamp.mSampleTime = 0;
UInt32 channelCount = 2;
AudioBufferList *bufferList = (AudioBufferList*)malloc(sizeof(AudioBufferList)+sizeof(AudioBuffer)*(channelCount-1));
bufferList->mNumberBuffers = channelCount;
for (int j=0; j<channelCount; j++)
{
AudioBuffer buffer = {0};
buffer.mNumberChannels = 1;
buffer.mDataByteSize = numberFrames*sizeof(SInt32);
buffer.mData = calloc(numberFrames,sizeof(SInt32));
bufferList->mBuffers[j] = buffer;
}
CheckError(AudioUnitRender(outputUnit, &flags, &inTimeStamp, busNumber, numberFrames, bufferList), #"AudioUnitRender outputUnit");
CMSampleBufferRef sampleBufferRef = NULL;
CMFormatDescriptionRef format = NULL;
CMSampleTimingInfo timing = { CMTimeMake(1, 44100), kCMTimeZero, kCMTimeInvalid };
AudioStreamBasicDescription audioFormat = self.audioFormat;
CheckError(CMAudioFormatDescriptionCreate(kCFAllocatorDefault, &audioFormat, 0, NULL, 0, NULL, NULL, &format), #"CMAudioFormatDescriptionCreate");
CheckError(CMSampleBufferCreate(kCFAllocatorDefault, NULL, false, NULL, NULL, format, numberFrames, 1, &timing, 0, NULL, &sampleBufferRef), #"CMSampleBufferCreate");
CheckError(CMSampleBufferSetDataBufferFromAudioBufferList(sampleBufferRef, kCFAllocatorDefault, kCFAllocatorDefault, 0, bufferList), #"CMSampleBufferSetDataBufferFromAudioBufferList");
return sampleBufferRef;
}
static OSStatus playbackCallback(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData)
{
int numberOfChannels = ioData->mBuffers[0].mNumberChannels;
SInt16 *outSample = (SInt16 *)ioData->mBuffers[0].mData;
/
memset(outSample, 0, ioData->mBuffers[0].mDataByteSize);
MyAudioPlayer *p = (__bridge MyAudioPlayer *)inRefCon;
if (p.hasBuffer){
int32_t availableBytes;
SInt16 *bufferTail = TPCircularBufferTail([p getBuffer], &availableBytes);
int32_t requestedBytesSize = inNumberFrames * kUnitSize * numberOfChannels;
int bytesToRead = MIN(availableBytes, requestedBytesSize);
memcpy(outSample, bufferTail, bytesToRead);
TPCircularBufferConsume([p getBuffer], bytesToRead);
if (availableBytes <= requestedBytesSize*2){
[p setReadyForMoreBytes];
}
if (availableBytes <= requestedBytesSize) {
p.hasBuffer = NO;
}
}
return noErr;
}
The CMSampleBufferRef I pass in looks valid (below is a dump of the object from the debugger)
CMSampleBuffer 0x7f87d2a03120 retainCount: 1 allocator: 0x103333180
invalid = NO
dataReady = NO
makeDataReadyCallback = 0x0
makeDataReadyRefcon = 0x0
formatDescription = <CMAudioFormatDescription 0x7f87d2a02b20 [0x103333180]> {
mediaType:'soun'
mediaSubType:'lpcm'
mediaSpecific: {
ASBD: {
mSampleRate: 44100.000000
mFormatID: 'lpcm'
mFormatFlags: 0xc2c
mBytesPerPacket: 2
mFramesPerPacket: 1
mBytesPerFrame: 2
mChannelsPerFrame: 1
mBitsPerChannel: 16 }
cookie: {(null)}
ACL: {(null)}
}
extensions: {(null)}
}
sbufToTrackReadiness = 0x0
numSamples = 512
sampleTimingArray[1] = {
{PTS = {0/1 = 0.000}, DTS = {INVALID}, duration = {1/44100 = 0.000}},
}
dataBuffer = 0x0
The buffer list looks like this
Printing description of bufferList:
(AudioBufferList *) bufferList = 0x00007f87d280b0a0
Printing description of bufferList->mNumberBuffers:
(UInt32) mNumberBuffers = 2
Printing description of bufferList->mBuffers:
(AudioBuffer [1]) mBuffers = {
[0] = (mNumberChannels = 1, mDataByteSize = 2048, mData = 0x00007f87d3008c00)
}
Really at a loss here, hoping someone can help. Thanks,
In case it matters i am debugging this in ios 8.3 simulator and the audio is coming from a mp4 that i shot on my iphone 6 then saved to my laptop.
I have read the following issues, however still to no avail, things are not working.
How to convert AudioBufferList to CMSampleBuffer?
Converting an AudioBufferList to a CMSampleBuffer Produces Unexpected Results
CMSampleBufferSetDataBufferFromAudioBufferList returning error 12731
core audio offline rendering GenericOutput
UPDATE
I poked around some more and notice that when my AudioBufferList right before AudioUnitRender runs looks like this:
bufferList->mNumberBuffers = 2,
bufferList->mBuffers[0].mNumberChannels = 1,
bufferList->mBuffers[0].mDataByteSize = 2048
mDataByteSize is numberFrames*sizeof(SInt32), which is 512 * 4. When I look at the AudioBufferList passed in playbackCallback, the list looks like this:
bufferList->mNumberBuffers = 1,
bufferList->mBuffers[0].mNumberChannels = 1,
bufferList->mBuffers[0].mDataByteSize = 1024
not really sure where that other buffer is going, or the other 1024 byte size...
if when i get finished calling Redner if I do something like this
AudioBufferList newbuff;
newbuff.mNumberBuffers = 1;
newbuff.mBuffers[0] = bufferList->mBuffers[0];
newbuff.mBuffers[0].mDataByteSize = 1024;
and pass newbuff off to CMSampleBufferSetDataBufferFromAudioBufferList the error goes away.
If I try setting the size of BufferList to have 1 mNumberBuffers or its mDataByteSize to be numberFrames*sizeof(SInt16) I get a -50 when calling AudioUnitRender
UPDATE 2
I hooked up a render callback so I can inspect the output when I play the sound over the speakers. I noticed that the output that goes to the speakers also has a AudioBufferList with 2 buffers, and the mDataByteSize during the input callback is 1024 and in the render callback its 2048, which is the same as I have been seeing when manually calling AudioUnitRender. When I inspect the data in the rendered AudioBufferList I notice that the bytes in the 2 buffers are the same, which means I can just ignore the second buffer. But I am not sure how to handle the fact that the data is 2048 in size after being rendered instead of 1024 as it's being taken in. Any ideas on why that could be happening? Is it in more of a raw form after going through the audio graph and that is why the size is doubling?
Sounds like the issue you're dealing with is because of a discrepancy in the number of channels. The reason you're seeing data in blocks of 2048 instead of 1024 is because it is feeding you back two channels (stereo). Check to make sure all of your audio units are properly configured to use mono throughout the entire audio graph, including the Pitch Unit and any audio format descriptions.
One thing to especially beware of is that calls to AudioUnitSetProperty can fail - so be sure to wrap those in CheckError() as well.
I'm trying to decode a raw stream of .H264 video data but I can't find a way to create a proper
- (void)decodeFrameWithNSData:(NSData*)data presentationTime:
(CMTime)presentationTime
{
#autoreleasepool {
CMSampleBufferRef sampleBuffer = NULL;
CMBlockBufferRef blockBuffer = NULL;
VTDecodeInfoFlags infoFlags;
int sourceFrame;
if( dSessionRef == NULL )
[self createDecompressionSession];
CMSampleTimingInfo timingInfo ;
timingInfo.presentationTimeStamp = presentationTime;
timingInfo.duration = CMTimeMake(1,100000000);
timingInfo.decodeTimeStamp = kCMTimeInvalid;
//Creates block buffer from NSData
OSStatus status = CMBlockBufferCreateWithMemoryBlock(CFAllocatorGetDefault(), (void*)data.bytes,data.length*sizeof(char), CFAllocatorGetDefault(), NULL, 0, data.length*sizeof(char), 0, &blockBuffer);
//Creates CMSampleBuffer to feed decompression session
status = CMSampleBufferCreateReady(CFAllocatorGetDefault(), blockBuffer,self.encoderVideoFormat,1,1,&timingInfo, 0, 0, &sampleBuffer);
status = VTDecompressionSessionDecodeFrame(dSessionRef,sampleBuffer, kVTDecodeFrame_1xRealTimePlayback, &sourceFrame,&infoFlags);
if(status != noErr) {
NSLog(#"Decode with data error %d",status);
}
}
}
At the end of the call I'm getting -12911 error in VTDecompressionSessionDecodeFrame that translates to kVTVideoDecoderMalfunctionErr which after reading this [post] pointed me that I should make a VideoFormatDescriptor using CMVideoFormatDescriptionCreateFromH264ParameterSets. But how can I create a new VideoFormatDescription if I don't have information of the currentSps or currentPps? How can I get that information from my raw .H264 streaming?
CMFormatDescriptionRef decoderFormatDescription;
const uint8_t* const parameterSetPointers[2] =
{ (const uint8_t*)[currentSps bytes], (const uint8_t*)[currentPps bytes] };
const size_t parameterSetSizes[2] =
{ [currentSps length], [currentPps length] };
status = CMVideoFormatDescriptionCreateFromH264ParameterSets(NULL,
2,
parameterSetPointers,
parameterSetSizes,
4,
&decoderFormatDescription);
Thanks in advance,
Marcos
[post] : Decoding H264 VideoToolkit API fails with Error -8971 in VTDecompressionSessionCreate
You you MUST call CMVideoFormatDescriptionCreateFromH264ParameterSets first. The SPS/PPS may be stored/transmitted separately from the video stream. Or may come inline.
Note that for VTDecompressionSessionDecodeFrame your NALUs must be preceded with a size, and not a start code.
You can read more here:
Possible Locations for Sequence/Picture Parameter Set(s) for H.264 Stream
My application records streaming audio on iPhone. My problem is that a small percent (~2%) of the recordings are corrupted. They appear to have some audio buffers duplicated.
For example listen to this file.
Edit: A surprising thing is that looking closely at the data using Audacity shows the repeating parts are very very similar but not identical. Since FLAC (the format I use for encoding the audio) is a loss-less compression, I guess this is not a bug in the streaming/encoding but the problem originates at the data that comes from the microphone!
Below is the code I use to setup the audio recording streaming - is there anything wrong with it?
// see functions implementation below
- (void)startRecording
{
dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0)
, ^{
[self setUpRecordQueue];
[self setUpRecordQueueBuffers];
[self primeRecordQueueBuffers];
AudioQueueStart(recordQueue, NULL);
});
}
// this is called only once before any recording takes place
- (void)setUpAudioFormat
{
AudioSessionInitialize(
NULL,
NULL,
nil,
(__bridge void *)(self)
);
UInt32 sessionCategory = kAudioSessionCategory_PlayAndRecord;
AudioSessionSetProperty(
kAudioSessionProperty_AudioCategory,
sizeof(sessionCategory),
&sessionCategory
);
AudioSessionSetActive(true);
audioFormat.mFormatID = kAudioFormatLinearPCM;
audioFormat.mSampleRate = SAMPLE_RATE;//16000.0;
audioFormat.mChannelsPerFrame = CHANNELS;//1;
audioFormat.mBitsPerChannel = 16;
audioFormat.mFramesPerPacket = 1;
audioFormat.mBytesPerFrame = audioFormat.mChannelsPerFrame * sizeof(SInt16);
audioFormat.mBytesPerPacket = audioFormat.mBytesPerFrame * audioFormat.mFramesPerPacket;
audioFormat.mFormatFlags = kLinearPCMFormatFlagIsSignedInteger | kLinearPCMFormatFlagIsPacked;
bufferNumPackets = 2048; // must be power of 2 for FFT!
bufferByteSize = [self byteSizeForNumPackets:bufferNumPackets];
}
// I suspect the duplicate buffers arrive here:
static void recordCallback(
void* inUserData,
AudioQueueRef inAudioQueue,
AudioQueueBufferRef inBuffer,
const AudioTimeStamp* inStartTime,
UInt32 inNumPackets,
const AudioStreamPacketDescription* inPacketDesc)
{
Recorder* recorder = (__bridge Recorder*) inUserData;
if (inNumPackets > 0)
{
// append the buffer to FLAC encoder
[recorder recordedBuffer:inBuffer->mAudioData byteSize:inBuffer->mAudioDataByteSize packetsNum:inNumPackets];
}
AudioQueueEnqueueBuffer(inAudioQueue, inBuffer, 0, NULL);
}
- (void)setUpRecordQueue
{
OSStatus errorStatus = AudioQueueNewInput(
&audioFormat,
recordCallback,
(__bridge void *)(self), // userData
CFRunLoopGetMain(), // run loop
NULL, // run loop mode
0, // flags
&recordQueue);
UInt32 trueValue = true;
AudioQueueSetProperty(recordQueue,kAudioQueueProperty_EnableLevelMetering,&trueValue,sizeof (UInt32));
}
- (void)setUpRecordQueueBuffers
{
for (int t = 0; t < NUMBER_AUDIO_DATA_BUFFERS; ++t)
{
OSStatus errorStatus = AudioQueueAllocateBuffer(
recordQueue,
bufferByteSize,
&recordQueueBuffers[t]);
}
}
- (void)primeRecordQueueBuffers
{
for (int t = 0; t < NUMBER_AUDIO_DATA_BUFFERS; ++t)
{
OSStatus errorStatus = AudioQueueEnqueueBuffer(
recordQueue,
recordQueueBuffers[t],
0,
NULL);
}
}
Turns out there was a rare bug allowing multiple recordings to start at nearly the same time - so two recordings took place in parallel but sent the audio buffers to the same callback, making the distorted repeating buffers in the encoded recordings...
I'm looking on this example http://teragonaudio.com/article/How-to-do-realtime-recording-with-effect-processing-on-iOS.html
and i want to turn off my output. I try to change: kAudioSessionCategory_PlayAndRecord to kAudioSessionCategory_RecordAudio but this is not working. I also try to get rid off:
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Output, 1, &streamDescription, sizeof(streamDescription)) != noErr) {
return 1;
}
Becouse i want to get sound from microphone but not playing it. But not matter what i do when my sound get to renderCallback method there is a -50 error. When audio is automatically play on output everything works fine...
Update with code:
using namespace std;
AudioUnit *audioUnit = NULL;
float *convertedSampleBuffer = NULL;
int initAudioSession() {
audioUnit = (AudioUnit*)malloc(sizeof(AudioUnit));
if(AudioSessionInitialize(NULL, NULL, NULL, NULL) != noErr) {
return 1;
}
if(AudioSessionSetActive(true) != noErr) {
return 1;
}
UInt32 sessionCategory = kAudioSessionCategory_PlayAndRecord;
if(AudioSessionSetProperty(kAudioSessionProperty_AudioCategory,
sizeof(UInt32), &sessionCategory) != noErr) {
return 1;
}
Float32 bufferSizeInSec = 0.02f;
if(AudioSessionSetProperty(kAudioSessionProperty_PreferredHardwareIOBufferDuration,
sizeof(Float32), &bufferSizeInSec) != noErr) {
return 1;
}
UInt32 overrideCategory = 1;
if(AudioSessionSetProperty(kAudioSessionProperty_OverrideCategoryDefaultToSpeaker,
sizeof(UInt32), &overrideCategory) != noErr) {
return 1;
}
// There are many properties you might want to provide callback functions for:
// kAudioSessionProperty_AudioRouteChange
// kAudioSessionProperty_OverrideCategoryEnableBluetoothInput
// etc.
return 0;
}
OSStatus renderCallback(void *userData, AudioUnitRenderActionFlags *actionFlags,
const AudioTimeStamp *audioTimeStamp, UInt32 busNumber,
UInt32 numFrames, AudioBufferList *buffers) {
OSStatus status = AudioUnitRender(*audioUnit, actionFlags, audioTimeStamp,
1, numFrames, buffers);
int doOutput = 0;
if(status != noErr) {
return status;
}
if(convertedSampleBuffer == NULL) {
// Lazy initialization of this buffer is necessary because we don't
// know the frame count until the first callback
convertedSampleBuffer = (float*)malloc(sizeof(float) * numFrames);
baseTime = (float)QRealTimer::getUptimeInMilliseconds();
}
SInt16 *inputFrames = (SInt16*)(buffers->mBuffers->mData);
// If your DSP code can use integers, then don't bother converting to
// floats here, as it just wastes CPU. However, most DSP algorithms rely
// on floating point, and this is especially true if you are porting a
// VST/AU to iOS.
int i;
for( i = numFrames; i < fftlength; i++ ) // Shifting buffer
x_inbuf[i - numFrames] = x_inbuf[i];
for( i = 0; i < numFrames; i++) {
x_inbuf[i + x_phase] = (float)inputFrames[i] / (float)32768;
}
if( x_phase + numFrames == fftlength )
{
x_alignment.SigProc_frontend(x_inbuf); // Signal processing front-end (FFT!)
doOutput = x_alignment.Align();
/// Output as text! In the real-time version,
// this is where we update visualisation callbacks and launch other services
if ((doOutput) & (x_netscore.isEvent(x_alignment.Position()))
&(x_alignment.lastAction()<x_alignment.Position()) )
{
// here i want to do something with my input!
}
}
else
x_phase += numFrames;
return noErr;
}
int initAudioStreams(AudioUnit *audioUnit) {
UInt32 audioCategory = kAudioSessionCategory_PlayAndRecord;
if(AudioSessionSetProperty(kAudioSessionProperty_AudioCategory,
sizeof(UInt32), &audioCategory) != noErr) {
return 1;
}
UInt32 overrideCategory = 1;
if(AudioSessionSetProperty(kAudioSessionProperty_OverrideCategoryDefaultToSpeaker,
sizeof(UInt32), &overrideCategory) != noErr) {
// Less serious error, but you may want to handle it and bail here
}
AudioComponentDescription componentDescription;
componentDescription.componentType = kAudioUnitType_Output;
componentDescription.componentSubType = kAudioUnitSubType_RemoteIO;
componentDescription.componentManufacturer = kAudioUnitManufacturer_Apple;
componentDescription.componentFlags = 0;
componentDescription.componentFlagsMask = 0;
AudioComponent component = AudioComponentFindNext(NULL, &componentDescription);
if(AudioComponentInstanceNew(component, audioUnit) != noErr) {
return 1;
}
UInt32 enable = 1;
if(AudioUnitSetProperty(*audioUnit, kAudioOutputUnitProperty_EnableIO,
kAudioUnitScope_Input, 1, &enable, sizeof(UInt32)) != noErr) {
return 1;
}
AURenderCallbackStruct callbackStruct;
callbackStruct.inputProc = renderCallback; // Render function
callbackStruct.inputProcRefCon = NULL;
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_SetRenderCallback,
kAudioUnitScope_Input, 0, &callbackStruct,
sizeof(AURenderCallbackStruct)) != noErr) {
return 1;
}
AudioStreamBasicDescription streamDescription;
// You might want to replace this with a different value, but keep in mind that the
// iPhone does not support all sample rates. 8kHz, 22kHz, and 44.1kHz should all work.
streamDescription.mSampleRate = 44100;
// Yes, I know you probably want floating point samples, but the iPhone isn't going
// to give you floating point data. You'll need to make the conversion by hand from
// linear PCM <-> float.
streamDescription.mFormatID = kAudioFormatLinearPCM;
// This part is important!
streamDescription.mFormatFlags = kAudioFormatFlagIsSignedInteger |
kAudioFormatFlagsNativeEndian |
kAudioFormatFlagIsPacked;
streamDescription.mBitsPerChannel = 16;
// 1 sample per frame, will always be 2 as long as 16-bit samples are being used
streamDescription.mBytesPerFrame = 2;
streamDescription.mChannelsPerFrame = 1;
streamDescription.mBytesPerPacket = streamDescription.mBytesPerFrame *
streamDescription.mChannelsPerFrame;
// Always should be set to 1
streamDescription.mFramesPerPacket = 1;
// Always set to 0, just to be sure
streamDescription.mReserved = 0;
// Set up input stream with above properties
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Input, 0, &streamDescription, sizeof(streamDescription)) != noErr) {
return 1;
}
// Ditto for the output stream, which we will be sending the processed audio to
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_StreamFormat,
kAudioUnitScope_Output, 1, &streamDescription, sizeof(streamDescription)) != noErr) {
return 1;
}
return 0;
}
int startAudioUnit(AudioUnit *audioUnit) {
if(AudioUnitInitialize(*audioUnit) != noErr) {
return 1;
}
if(AudioOutputUnitStart(*audioUnit) != noErr) {
return 1;
}
return 0;
}
And calling from my VC:
initAudioSession();
initAudioStreams( audioUnit);
startAudioUnit( audioUnit);
If you want only recording, no playback, simply comment out the line that sets renderCallback:
AURenderCallbackStruct callbackStruct;
callbackStruct.inputProc = renderCallback; // Render function
callbackStruct.inputProcRefCon = NULL;
if(AudioUnitSetProperty(*audioUnit, kAudioUnitProperty_SetRenderCallback,
kAudioUnitScope_Input, 0, &callbackStruct,
sizeof(AURenderCallbackStruct)) != noErr) {
return 1;
}
Update after seeing code:
As I suspected, you're missing input callback. Add these lines:
// at top:
#define kInputBus 1
AURenderCallbackStruct callbackStruct;
/**/
callbackStruct.inputProc = &ALAudioUnit::recordingCallback;
callbackStruct.inputProcRefCon = this;
status = AudioUnitSetProperty(audioUnit,
kAudioOutputUnitProperty_SetInputCallback,
kAudioUnitScope_Global,
kInputBus,
&callbackStruct,
sizeof(callbackStruct));
Now in your recordingCallback:
OSStatus ALAudioUnit::recordingCallback(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData)
{
// TODO: Use inRefCon to access our interface object to do stuff
// Then, use inNumberFrames to figure out how much data is available, and make
// that much space available in buffers in an AudioBufferList.
// Then:
// Obtain recorded samples
OSStatus status;
ALAudioUnit *pThis = reinterpret_cast<ALAudioUnit*>(inRefCon);
if (!pThis)
return noErr;
//assert (pThis->m_nMaxSliceFrames >= inNumberFrames);
pThis->recorderBufferList->GetBufferList().mBuffers[0].mDataByteSize = inNumberFrames * pThis->m_recorderSBD.mBytesPerFrame;
status = AudioUnitRender(pThis->audioUnit,
ioActionFlags,
inTimeStamp,
inBusNumber,
inNumberFrames,
&pThis->recorderBufferList->GetBufferList());
THROW_EXCEPTION_IF_ERROR(status, "error rendering audio unit");
// If we're not playing, I don't care about the data, simply discard it
if (!pThis->playbackState || pThis->isSeeking) return noErr;
// Now, we have the samples we just read sitting in buffers in bufferList
pThis->DoStuffWithTheRecordedAudio(inNumberFrames, pThis->recorderBufferList, inTimeStamp);
return noErr;
}
Btw, I'm allocating my own buffer instead of using the one provided by AudioUnit. You might want to change those parts if you want to use AudioUnit allocated buffer.
Update:
How to allocate own buffer:
recorderBufferList = new AUBufferList();
recorderBufferList->Allocate(m_recorderSBD, m_nMaxSliceFrames);
recorderBufferList->PrepareBuffer(m_recorderSBD, m_nMaxSliceFrames);
Also, if you're doing this, tell AudioUnit to not allocate buffers:
// Disable buffer allocation for the recorder (optional - do this if we want to pass in our own)
flag = 0;
status = AudioUnitSetProperty(audioUnit,
kAudioUnitProperty_ShouldAllocateBuffer,
kAudioUnitScope_Input,
kInputBus,
&flag,
sizeof(flag));
You'll need to include CoreAudio utility classes
Thanks for #Mar0ux 's answer. Whoever got here looking for complete sample code doing this can take a look here:
https://code.google.com/p/ios-coreaudio-example/
I am doing a similar app working with the same code and I found that you can end playback by changing the enumeration kAudioSessionCategory_PlayAndRecord to RecordAudio
int initAudioStreams(AudioUnit *audioUnit) {
UInt32 audioCategory = kAudioSessionCategory_RecordAudio;
if(AudioSessionSetProperty(kAudioSessionProperty_AudioCategory,
sizeof(UInt32), &audioCategory) != noErr) {
return 1;
}
This stopped the feedback between mic and speaker on my hardware.