使用 WASAPI 录制音频流
Posted
技术标签:
【中文标题】使用 WASAPI 录制音频流【英文标题】：Record an audio stream with WASAPI 【发布时间】：2020-10-12 12:46:20 【问题描述】：我正在阅读诸如 Capturing a stream 或 Loopback recording 之类的文档，但我找不到一个关于如何从 Loopback 音频设备（有时使用 Windows WASAPI 称为“你所听到的”、“立体声混音”）。
您能否提供一个简单的可重现示例，展示如何使用 C++ 从 WASAPI 设备循环录制音频块？
这是 Python 中的一个类似（工作）示例：
import soundcard as sc # installed with: pip install soundcard
lb = sc.all_microphones(include_loopback=True)[0]
with lb.recorder(samplerate=44100) as mic:
while True:
data = mic.record(numframes=None)
print(data) # chunks of audio data (448 samples x 2 channels as an array by default)
【问题讨论】：
"在捕获流中的代码示例中，RecordAudiostream函数可以很容易地修改为配置环回模式捕获流。"你关注this part instructions看有帮助吗？ 我看过这个@RitaHan-MSFT，但我什至没有实现编译原始代码docs.microsoft.com/en-us/windows/win32/coreaudio/…：没有包含，没有构建指令等。这些细节并不是很明显在这种情况下。如果我能先实现构建这个，那么，是的，我想我将能够适应“loopback-mode capture”。 更多详细信息请查看此博客：Sample - WASAPI loopback capture (record what you hear). @RitaHan-MSFT 你的意思是github.com/mvaneerde/blog/tree/develop/loopback-capture/…？看起来很有希望，但它被分割在许多 cpp 文件中，不是很容易理解，但我会研究这个，你是对的。最好的办法是在此处 docs.microsoft.com/en-us/windows/win32/coreaudio/… 更新 MSDN 页面，并提供可重现的代码（包含构建指令、包含、标头等） 它包含一个VS解决方案文件，使用Visual Studio很容易构建和运行。 【参考方案1】：这是环回模式音频捕获的示例。
根据Capturing a stream的文档，将Loopback recording指出的一些版本制作如下：
// In the call to the IMMDeviceEnumerator::GetDefaultAudioEndpoint method, change the first parameter (dataFlow) from eCapture to eRender.
hr = pEnumerator->GetDefaultAudioEndpoint(
eRender, eConsole, &pDevice);
...
// In the call to the IAudioClient::Initialize method, change the value of the second parameter (StreamFlags) from 0 to AUDCLNT_STREAMFLAGS_LOOPBACK.
hr = pAudioClient->Initialize(
AUDCLNT_SHAREMODE_SHARED,
AUDCLNT_STREAMFLAGS_LOOPBACK,
hnsRequestedDuration,
0,
pwfx,
NULL);
文档中缺少的部分：CopyData() 和写入文件函数（WriteWaveHeader() 和 FinishWaveFile()）。以下显示了这些功能实现的示例。更多详细信息请参阅博客Sample - WASAPI loopback capture (record what you hear)。
HRESULT MyAudioSink::CopyData(BYTE* pData, UINT32 NumFrames, BOOL* pDone, WAVEFORMATEX* pwfx, HMMIO hFile)
HRESULT hr = S_OK;
if (0 == NumFrames)
wprintf(L"IAudioCaptureClient::GetBuffer said to read 0 frames\n");
return E_UNEXPECTED;
LONG lBytesToWrite = NumFrames * pwfx->nBlockAlign;
#pragma prefast(suppress: __WARNING_INCORRECT_ANNOTATION, "IAudioCaptureClient::GetBuffer SAL annotation implies a 1-byte buffer")
LONG lBytesWritten = mmioWrite(hFile, reinterpret_cast<PCHAR>(pData), lBytesToWrite);
if (lBytesToWrite != lBytesWritten)
wprintf(L"mmioWrite wrote %u bytes : expected %u bytes", lBytesWritten, lBytesToWrite);
return E_UNEXPECTED;
static int CallCount = 0;
cout << "CallCount = " << CallCount++ << "NumFrames: " << NumFrames << endl ;
if (clock() > 10 * CLOCKS_PER_SEC) //Record 10 seconds. From the first time call clock() at the beginning of the main().
*pDone = true;
return S_OK;
HRESULT WriteWaveHeader(HMMIO hFile, LPCWAVEFORMATEX pwfx, MMCKINFO* pckRIFF, MMCKINFO* pckData)
MMRESULT result;
// make a RIFF/WAVE chunk
pckRIFF->ckid = MAKEFOURCC('R', 'I', 'F', 'F');
pckRIFF->fccType = MAKEFOURCC('W', 'A', 'V', 'E');
result = mmioCreateChunk(hFile, pckRIFF, MMIO_CREATERIFF);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"RIFF/WAVE\") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'fmt ' chunk (within the RIFF/WAVE chunk)
MMCKINFO chunk;
chunk.ckid = MAKEFOURCC('f', 'm', 't', ' ');
result = mmioCreateChunk(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"fmt \") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// write the WAVEFORMATEX data to it
LONG lBytesInWfx = sizeof(WAVEFORMATEX) + pwfx->cbSize;
LONG lBytesWritten =
mmioWrite(
hFile,
reinterpret_cast<PCHAR>(const_cast<LPWAVEFORMATEX>(pwfx)),
lBytesInWfx
);
if (lBytesWritten != lBytesInWfx)
wprintf(L"mmioWrite(fmt data) wrote %u bytes; expected %u bytes", lBytesWritten, lBytesInWfx);
return E_FAIL;
// ascend from the 'fmt ' chunk
result = mmioAscend(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"fmt \" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'fact' chunk whose data is (DWORD)0
chunk.ckid = MAKEFOURCC('f', 'a', 'c', 't');
result = mmioCreateChunk(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"fmt \") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// write (DWORD)0 to it
// this is cleaned up later
DWORD frames = 0;
lBytesWritten = mmioWrite(hFile, reinterpret_cast<PCHAR>(&frames), sizeof(frames));
if (lBytesWritten != sizeof(frames))
wprintf(L"mmioWrite(fact data) wrote %u bytes; expected %u bytes", lBytesWritten, (UINT32)sizeof(frames));
return E_FAIL;
// ascend from the 'fact' chunk
result = mmioAscend(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"fact\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'data' chunk and leave the data pointer there
pckData->ckid = MAKEFOURCC('d', 'a', 't', 'a');
result = mmioCreateChunk(hFile, pckData, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"data\") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
return S_OK;
HRESULT FinishWaveFile(HMMIO hFile, MMCKINFO* pckRIFF, MMCKINFO* pckData)
MMRESULT result;
result = mmioAscend(hFile, pckData, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"data\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
result = mmioAscend(hFile, pckRIFF, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"RIFF/WAVE\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
return S_OK;
在pAudioClient->Start() 之前致电WriteWaveHeader。在pAudioClient->Stop() 之后调用FinishWaveFile。
因此，它会录制大约 10 秒在您的 Windows 上播放的音频。
更新 #1：
#include <Windows.h>
#include <mmsystem.h>
#include <mmdeviceapi.h>
#include <audioclient.h>
#include <time.h>
#include <iostream>
int main()
clock();
HRESULT hr = CoInitializeEx(NULL, COINIT_MULTITHREADED);
// Create file
MMIOINFO mi = 0 ;
hFile = mmioOpen(
// some flags cause mmioOpen write to this buffer
// but not any that we're using
(LPWSTR)fileName,
&mi,
MMIO_WRITE | MMIO_CREATE
);
if (NULL == hFile)
wprintf(L"mmioOpen(\"%ls\", ...) failed. wErrorRet == %u", fileName, GetLastError());
return E_FAIL;
MyAudioSink AudioSink;
RecordAudioStream(&AudioSink);
mmioClose(hFile, 0);
CoUninitialize();
return 0;
编译命令：
cl -DUNICODE loopbackCapture.cpp /link winmm.lib user32.lib Kernel32.lib Ole32.lib
更新 #2：
#include <Windows.h>
#include <mmsystem.h>
#include <mmdeviceapi.h>
#include <audioclient.h>
#include <time.h>
#include <iostream>
using namespace std;
#pragma comment(lib, "Winmm.lib")
WCHAR fileName[] = L"loopback-capture.wav";
BOOL bDone = FALSE;
HMMIO hFile = NULL;
// 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);
class MyAudioSink
public:
HRESULT CopyData(BYTE* pData, UINT32 NumFrames, BOOL* pDone, WAVEFORMATEX* pwfx, HMMIO hFile);
;
HRESULT WriteWaveHeader(HMMIO hFile, LPCWAVEFORMATEX pwfx, MMCKINFO* pckRIFF, MMCKINFO* pckData);
HRESULT FinishWaveFile(HMMIO hFile, MMCKINFO* pckRIFF, MMCKINFO* pckData);
HRESULT RecordAudioStream(MyAudioSink* pMySink);
int main()
clock();
HRESULT hr = CoInitializeEx(NULL, COINIT_MULTITHREADED);
// Create file
MMIOINFO mi = 0 ;
hFile = mmioOpen(
// some flags cause mmioOpen write to this buffer
// but not any that we're using
(LPWSTR)fileName,
&mi,
MMIO_WRITE | MMIO_CREATE
);
if (NULL == hFile)
wprintf(L"mmioOpen(\"%ls\", ...) failed. wErrorRet == %u", fileName, GetLastError());
return E_FAIL;
MyAudioSink AudioSink;
RecordAudioStream(&AudioSink);
mmioClose(hFile, 0);
CoUninitialize();
return 0;
HRESULT MyAudioSink::CopyData(BYTE* pData, UINT32 NumFrames, BOOL* pDone, WAVEFORMATEX* pwfx, HMMIO hFile)
HRESULT hr = S_OK;
if (0 == NumFrames)
wprintf(L"IAudioCaptureClient::GetBuffer said to read 0 frames\n");
return E_UNEXPECTED;
LONG lBytesToWrite = NumFrames * pwfx->nBlockAlign;
#pragma prefast(suppress: __WARNING_INCORRECT_ANNOTATION, "IAudioCaptureClient::GetBuffer SAL annotation implies a 1-byte buffer")
LONG lBytesWritten = mmioWrite(hFile, reinterpret_cast<PCHAR>(pData), lBytesToWrite);
if (lBytesToWrite != lBytesWritten)
wprintf(L"mmioWrite wrote %u bytes : expected %u bytes", lBytesWritten, lBytesToWrite);
return E_UNEXPECTED;
static int CallCount = 0;
cout << "CallCount = " << CallCount++ << "NumFrames: " << NumFrames << endl ;
if (clock() > 10 * CLOCKS_PER_SEC) //Record 10 seconds. From the first time call clock() at the beginning of the main().
*pDone = true;
return S_OK;
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;
BYTE* pData;
DWORD flags;
MMCKINFO ckRIFF = 0 ;
MMCKINFO ckData = 0 ;
hr = CoCreateInstance(
CLSID_MMDeviceEnumerator, NULL,
CLSCTX_ALL, IID_IMMDeviceEnumerator,
(void**)& pEnumerator);
EXIT_ON_ERROR(hr)
hr = pEnumerator->GetDefaultAudioEndpoint(
eRender, 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,
AUDCLNT_STREAMFLAGS_LOOPBACK,
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)
hr = WriteWaveHeader((HMMIO)hFile, pwfx, &ckRIFF, &ckData);
if (FAILED(hr))
// WriteWaveHeader does its own logging
return 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, pwfx, (HMMIO)hFile);
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)
hr = FinishWaveFile((HMMIO)hFile, &ckData, &ckRIFF);
if (FAILED(hr))
// FinishWaveFile does it's own logging
return hr;
Exit:
CoTaskMemFree(pwfx);
SAFE_RELEASE(pEnumerator)
SAFE_RELEASE(pDevice)
SAFE_RELEASE(pAudioClient)
SAFE_RELEASE(pCaptureClient)
return hr;
HRESULT WriteWaveHeader(HMMIO hFile, LPCWAVEFORMATEX pwfx, MMCKINFO* pckRIFF, MMCKINFO* pckData)
MMRESULT result;
// make a RIFF/WAVE chunk
pckRIFF->ckid = MAKEFOURCC('R', 'I', 'F', 'F');
pckRIFF->fccType = MAKEFOURCC('W', 'A', 'V', 'E');
result = mmioCreateChunk(hFile, pckRIFF, MMIO_CREATERIFF);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"RIFF/WAVE\") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'fmt ' chunk (within the RIFF/WAVE chunk)
MMCKINFO chunk;
chunk.ckid = MAKEFOURCC('f', 'm', 't', ' ');
result = mmioCreateChunk(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"fmt \") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// write the WAVEFORMATEX data to it
LONG lBytesInWfx = sizeof(WAVEFORMATEX) + pwfx->cbSize;
LONG lBytesWritten =
mmioWrite(
hFile,
reinterpret_cast<PCHAR>(const_cast<LPWAVEFORMATEX>(pwfx)),
lBytesInWfx
);
if (lBytesWritten != lBytesInWfx)
wprintf(L"mmioWrite(fmt data) wrote %u bytes; expected %u bytes", lBytesWritten, lBytesInWfx);
return E_FAIL;
// ascend from the 'fmt ' chunk
result = mmioAscend(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"fmt \" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'fact' chunk whose data is (DWORD)0
chunk.ckid = MAKEFOURCC('f', 'a', 'c', 't');
result = mmioCreateChunk(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"fmt \") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// write (DWORD)0 to it
// this is cleaned up later
DWORD frames = 0;
lBytesWritten = mmioWrite(hFile, reinterpret_cast<PCHAR>(&frames), sizeof(frames));
if (lBytesWritten != sizeof(frames))
wprintf(L"mmioWrite(fact data) wrote %u bytes; expected %u bytes", lBytesWritten, (UINT32)sizeof(frames));
return E_FAIL;
// ascend from the 'fact' chunk
result = mmioAscend(hFile, &chunk, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"fact\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
// make a 'data' chunk and leave the data pointer there
pckData->ckid = MAKEFOURCC('d', 'a', 't', 'a');
result = mmioCreateChunk(hFile, pckData, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioCreateChunk(\"data\") failed: MMRESULT = 0x%08x", result);
return E_FAIL;
return S_OK;
HRESULT FinishWaveFile(HMMIO hFile, MMCKINFO* pckRIFF, MMCKINFO* pckData)
MMRESULT result;
result = mmioAscend(hFile, pckData, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"data\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
result = mmioAscend(hFile, pckRIFF, 0);
if (MMSYSERR_NOERROR != result)
wprintf(L"mmioAscend(\"RIFF/WAVE\" failed: MMRESULT = 0x%08x", result);
return E_FAIL;
return S_OK;
【讨论】：
非常感谢！我会试试这个。你可以包括相关的标题包括等和main()，以便它可以重现吗？像cl test.cpp /link winmm.lib user32.lib Kernel32.lib /subsystem:windows /entry:wmainCRTStartup 这样的东西对于未来的参考/未来的读者来说非常有用。
非常感谢@RitaHanMSFT 的更新。我们接近解决方案！还有一些错误：MyAudioSink 未定义为类等。您能否包含完整的 .cpp 代码？ （或者可能暂时将其粘贴到paste.ee 或类似的地方），我正在努力编译它。 PS：这里paste.ee/p/MA69P我尝试使用1）来自docs.microsoft.com/en-us/windows/win32/coreaudio/…的C++代码2）你的第二个代码块3）你的第三个代码块（“更新”）。
@Basj 请查看我的更新 #2 以获取完整的 .cpp 代码。仅将其用作参考，因为它还没有准备好用于生产环境。
非常感谢@RitaHanMSFT，我会尽快尝试！
谢谢，录音工作@RitaHanMSFT！ （我仍然无法打开.wav，可能标题中有一些错误，但我可以自己检查这部分）。还有一个小问题：当电脑上没有声音播放时，没有录制静音帧，你知道我们该如何解决这个问题吗？如果没有使用声卡，则应记录静音。以上是关于使用 WASAPI 录制音频流的主要内容，如果未能解决你的问题，请参考以下文章