涉及的接口有:
- IMMDeviceEnumerator
- IMMDevice
- IAudioClient
- IAudioCaptureClient
主要过程:
- 创建多媒体设备枚举器(IMMDeviceEnumerator)
- 通过多媒体设备枚举器获取声卡接口(IMMDevice)
- 通过声卡接口获取声卡客户端接口(IAudioClient)
- 通过声卡客户端接口(IAudioClient)可获取声卡输出的音频参数、初始化声卡、获取声卡输出缓冲区的大小、开启/停止对声卡输出的采集
- 通过声卡采集客户端接口(IAudioCaptureClient)可获取采集的声卡输出数据,并对内部缓冲区进行控制
- 通过声卡输出客户端接口(IAudioRenderClient)可将采集的声音数据写入声音输出设备的缓存单元,输出设备可以通过IAudioClient::GetService函数获取 IAudioRenderClient 接口。
参考网站:
https://docs.microsoft.com/zh-cn/windows/desktop/CoreAudio/capturing-a-stream
https://docs.microsoft.com/zh-cn/windows/desktop/CoreAudio/audio-endpoint-devices
微软例子:
//-----------------------------------------------------------
// 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.
//-----------------------------------------------------------
// 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(MyAudioSink *pMySink)
{
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 = 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);
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;
}