最近看obs的音频采集,发现它在采集音频时用到了两个方法:默认音频设备时采用CoreAudio、指定音频设备时采用DirectShow
对windows下的CoreAudio技术不是太熟,于是就认真学了一下。
参考微软官方文档:https://docs.microsoft.com/zh-cn/windows/desktop/CoreAudio/capturing-a-stream
//-----------------------------------------------------------
// Record an audio stream from the default audio capture
// device. The RecordAudioStream function allocates a shared
// buffer big enough to hold one second of PCM audio data.
// The function uses this buffer to stream data from the
// capture device. The main loop runs every 1/2 second.
//-----------------------------------------------------------
#include <mmdeviceapi.h>
#include <Audioclient.h>
#include <audiopolicy.h>
#include <devicetopology.h>
#include <endpointvolume.h>
#include <stdio.h>
// REFERENCE_TIME time units per second and per millisecond
#define REFTIMES_PER_SEC 10000000
#define REFTIMES_PER_MILLISEC 10000
#define EXIT_ON_ERROR(hres) \
if (FAILED(hres)) { goto Exit; }
#define SAFE_RELEASE(punk) \
if ((punk) != NULL) \
{ (punk)->Release(); (punk) = NULL; }
const CLSID CLSID_MMDeviceEnumerator = __uuidof(MMDeviceEnumerator);
const IID IID_IMMDeviceEnumerator = __uuidof(IMMDeviceEnumerator);
const IID IID_IAudioClient = __uuidof(IAudioClient);
const IID IID_IAudioCaptureClient = __uuidof(IAudioCaptureClient);
HRESULT RecordAudioStream()
{
HRESULT hr;
REFERENCE_TIME hnsRequestedDuration = REFTIMES_PER_SEC;
REFERENCE_TIME hnsActualDuration;
UINT32 bufferFrameCount;
UINT32 numFramesAvailable;
IMMDeviceEnumerator *pEnumerator = NULL;
IMMDevice *pDevice = NULL;
IAudioClient *pAudioClient = NULL;
IAudioCaptureClient *pCaptureClient = NULL;
WAVEFORMATEX *pwfx = NULL;
UINT32 packetLength = 0;
BOOL bDone = FALSE;
BYTE *pData;
DWORD flags;
hr = CoInitializeEx(NULL, COINIT_MULTITHREADED);
hr = CoCreateInstance(CLSID_MMDeviceEnumerator, NULL,CLSCTX_ALL, IID_IMMDeviceEnumerator,(void**)&pEnumerator);
EXIT_ON_ERROR(hr)
hr = pEnumerator->GetDefaultAudioEndpoint(eCapture, eConsole, &pDevice);
EXIT_ON_ERROR(hr)
hr = pDevice->Activate(IID_IAudioClient, CLSCTX_ALL,NULL, (void**)&pAudioClient);
EXIT_ON_ERROR(hr)
hr = pAudioClient->GetMixFormat(&pwfx);
EXIT_ON_ERROR(hr)
hr = pAudioClient->Initialize(AUDCLNT_SHAREMODE_SHARED,0,hnsRequestedDuration,0,pwfx,NULL);
EXIT_ON_ERROR(hr)
// Get the size of the allocated buffer.
hr = pAudioClient->GetBufferSize(&bufferFrameCount);
EXIT_ON_ERROR(hr)
hr = pAudioClient->GetService(IID_IAudioCaptureClient,(void**)&pCaptureClient);
EXIT_ON_ERROR(hr)
// Notify the audio sink which format to use.
//hr = pMySink->SetFormat(pwfx);
EXIT_ON_ERROR(hr)
// Calculate the actual duration of the allocated buffer.
hnsActualDuration = (double)REFTIMES_PER_SEC *bufferFrameCount / pwfx->nSamplesPerSec;
hr = pAudioClient->Start(); // Start recording.
EXIT_ON_ERROR(hr)
// Each loop fills about half of the shared buffer.
while (bDone == FALSE)
{
// Sleep for half the buffer duration.
Sleep(hnsActualDuration / REFTIMES_PER_MILLISEC / 2);
hr = pCaptureClient->GetNextPacketSize(&packetLength);
EXIT_ON_ERROR(hr)
while (packetLength != 0)
{
// Get the available data in the shared buffer.
hr = pCaptureClient->GetBuffer(&pData,&numFramesAvailable,&flags, NULL, NULL);
EXIT_ON_ERROR(hr)
if (flags & AUDCLNT_BUFFERFLAGS_SILENT)
{
pData = NULL; // Tell CopyData to write silence.
}
// Copy the available capture data to the audio sink.
//hr = pMySink->CopyData(
// pData, numFramesAvailable, &bDone);
printf("size=%d\n", numFramesAvailable);
EXIT_ON_ERROR(hr)
hr = pCaptureClient->ReleaseBuffer(numFramesAvailable);
EXIT_ON_ERROR(hr)
hr = pCaptureClient->GetNextPacketSize(&packetLength);
EXIT_ON_ERROR(hr)
}
}
hr = pAudioClient->Stop(); // Stop recording.
EXIT_ON_ERROR(hr)
Exit:
CoTaskMemFree(pwfx);
SAFE_RELEASE(pEnumerator)
SAFE_RELEASE(pDevice)
SAFE_RELEASE(pAudioClient)
SAFE_RELEASE(pCaptureClient)
return hr;
}
int main()
{
RecordAudioStream();
return 0;
}