I'm writing a CoreAudio backend for an audio library called XAL. Input buffers can be of various sample rates. I'm using a single audio unit for output. Idea is to convert the buffers and mix them prior to sending them to the audio unit.
Everything works as long as the input buffer has the same properties (sample rate, channel count, etc) as the output audio unit. Hence, the mixing part works.
However, I'm stuck with sample rate and channel count conversion. From what I figured out, this is easiest to do with Audio Converter Services API. I've managed to construct a converter; the idea is that the output format is the same as the output unit format, but possibly adjusted for purposes of the converter.
Audio converter is successfully constructed, but upon calling AudioConverterFillComplexBuffer(), I get output status error -50.
I'd love if I could get another set of eyeballs on this code. Problem is probably somewhere below AudioConverterNew(). Variable stream contains incoming (and outgoing) buffer data, and streamSize contains byte-size of incoming (and outgoing) buffer data.
What did I do wrong?
void CoreAudio_AudioManager::_convertStream(Buffer* buffer, unsigned char** stream, int *streamSize)
{
if (buffer->getBitsPerSample() != unitDescription.mBitsPerChannel ||
buffer->getChannels() != unitDescription.mChannelsPerFrame ||
buffer->getSamplingRate() != unitDescription.mSampleRate)
{
printf("INPUT STREAM SIZE: %d\n", *streamSize);
// describe the input format's description
AudioStreamBasicDescription inputDescription;
memset(&inputDescription, 0, sizeof(inputDescription));
inputDescription.mFormatID = kAudioFormatLinearPCM;
inputDescription.mFormatFlags = kLinearPCMFormatFlagIsPacked | kLinearPCMFormatFlagIsSignedInteger;
inputDescription.mChannelsPerFrame = buffer->getChannels();
inputDescription.mSampleRate = buffer->getSamplingRate();
inputDescription.mBitsPerChannel = buffer->getBitsPerSample();
inputDescription.mBytesPerFrame = (inputDescription.mBitsPerChannel * inputDescription.mChannelsPerFrame) / 8;
inputDescription.mFramesPerPacket = 1; //*streamSize / inputDescription.mBytesPerFrame;
inputDescription.mBytesPerPacket = inputDescription.mBytesPerFrame * inputDescription.mFramesPerPacket;
printf("INPUT : %lu bytes per packet for sample rate %g, channels %d\n", inputDescription.mBytesPerPacket, inputDescription.mSampleRate, inputDescription.mChannelsPerFrame);
// copy conversion output format's description from the
// output audio unit's description.
// then adjust framesPerPacket to match the input we'll be passing.
// framecount of our input stream is based on the input bytecount.
// output stream will have same number of frames, but different
// number of bytes.
AudioStreamBasicDescription outputDescription = unitDescription;
outputDescription.mFramesPerPacket = 1; //inputDescription.mFramesPerPacket;
outputDescription.mBytesPerPacket = outputDescription.mBytesPerFrame * outputDescription.mFramesPerPacket;
printf("OUTPUT : %lu bytes per packet for sample rate %g, channels %d\n", outputDescription.mBytesPerPacket, outputDescription.mSampleRate, outputDescription.mChannelsPerFrame);
// create an audio converter
AudioConverterRef audioConverter;
OSStatus acCreationResult = AudioConverterNew(&inputDescription, &outputDescription, &audioConverter);
printf("Created audio converter %p (status: %d)\n", audioConverter, acCreationResult);
if(!audioConverter)
{
// bail out
free(*stream);
*streamSize = 0;
*stream = (unsigned char*)malloc(0);
return;
}
// calculate number of bytes required for output of input stream.
// allocate buffer of adequate size.
UInt32 outputBytes = outputDescription.mBytesPerPacket * (*streamSize / inputDescription.mBytesPerFrame); // outputDescription.mFramesPerPacket * outputDescription.mBytesPerFrame;
unsigned char *outputBuffer = (unsigned char*)malloc(outputBytes);
memset(outputBuffer, 0, outputBytes);
printf("OUTPUT BYTES : %d\n", outputBytes);
// describe input data we'll pass into converter
AudioBuffer inputBuffer;
inputBuffer.mNumberChannels = inputDescription.mChannelsPerFrame;
inputBuffer.mDataByteSize = *streamSize;
inputBuffer.mData = *stream;
// describe output data buffers into which we can receive data.
AudioBufferList outputBufferList;
outputBufferList.mNumberBuffers = 1;
outputBufferList.mBuffers[0].mNumberChannels = outputDescription.mChannelsPerFrame;
outputBufferList.mBuffers[0].mDataByteSize = outputBytes;
outputBufferList.mBuffers[0].mData = outputBuffer;
// set output data packet size
UInt32 outputDataPacketSize = outputDescription.mBytesPerPacket;
// convert
OSStatus result = AudioConverterFillComplexBuffer(audioConverter, /* AudioConverterRef inAudioConverter */
CoreAudio_AudioManager::_converterComplexInputDataProc, /* AudioConverterComplexInputDataProc inInputDataProc */
&inputBuffer, /* void *inInputDataProcUserData */
&outputDataPacketSize, /* UInt32 *ioOutputDataPacketSize */
&outputBufferList, /* AudioBufferList *outOutputData */
NULL /* AudioStreamPacketDescription *outPacketDescription */
);
printf("Result: %d wheee\n", result);
// change "stream" to describe our output buffer.
// even if error occured, we'd rather have silence than unconverted audio.
free(*stream);
*stream = outputBuffer;
*streamSize = outputBytes;
// dispose of the audio converter
AudioConverterDispose(audioConverter);
}
}
OSStatus CoreAudio_AudioManager::_converterComplexInputDataProc(AudioConverterRef inAudioConverter,
UInt32* ioNumberDataPackets,
AudioBufferList* ioData,
AudioStreamPacketDescription** ioDataPacketDescription,
void* inUserData)
{
printf("Converter\n");
if(*ioNumberDataPackets != 1)
{
xal::log("_converterComplexInputDataProc cannot provide input data; invalid number of packets requested");
*ioNumberDataPackets = 0;
ioData->mNumberBuffers = 0;
return -50;
}
*ioNumberDataPackets = 1;
ioData->mNumberBuffers = 1;
ioData->mBuffers[0] = *(AudioBuffer*)inUserData;
*ioDataPacketDescription = NULL;
return 0;
}
