ffmpeg录制麦克风声音和pc内部声音(如播放歌曲)---混音

vs版本：vs2017
ffmpeg版本：
ffmpeg version N-102642-g864d1ef2fc Copyright © 2000-2021 the FFmpeg developers
built with gcc 8.1.0 (x86_64-win32-seh-rev0, Built by MinGW-W64 project)
configuration: --arch=x86_64 --disable-debug --enable-shared --disable-static --enable-gpl --enable-libx264 --extra-cflags=-I/usr/local/x264/include --extra-ldflags=’-L/usr/local/x264/lib -static’ --pkgconfigdir=/usr/local/x264/lib/pkgconfig --prefix=/home/ffmpeg_x264_dll
libavutil 57. 0.100 / 57. 0.100
libavcodec 59. 1.100 / 59. 1.100
libavformat 59. 2.101 / 59. 2.101
libavdevice 59. 0.100 / 59. 0.100
libavfilter 8. 0.101 / 8. 0.101
libswscale 6. 0.100 / 6. 0.100
libswresample 4. 0.100 / 4. 0.100
libpostproc 56. 0.100 / 56. 0.100
Hyper fast Audio and Video encoder

将麦克风声音和pc内部声音混合在一起时，最开始想到的是如同将声音和视频混在一起，这方面，大家可以看我写的一篇博客：ffmpeg录制桌面视频和麦克风音频(音视频同步)
我按照这种方式，创建了两路流，一路写入麦克风声音，一路写入电脑内部声音，但是最终生成的声音文件，无法达到播放的效果。
后面查了下，ffmpeg有提供混流的方式，下面不多说，直接上代码。

// FfmpegAudioTest.cpp : 此文件包含 "main" 函数。程序执行将在此处开始并结束。
//

#include <Windows.h>
#include <conio.h>

#ifdef	__cplusplus
extern "C"
{
   
   
#endif
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libswscale/swscale.h"
#include "libswresample/swresample.h"
#include "libavdevice/avdevice.h"
#include "libavutil/audio_fifo.h"
#include "libavutil/avutil.h"
#include "libavutil/fifo.h"
#include "libavutil/frame.h"

#include "libavfilter/avfilter.h"
#include "libavfilter/buffersink.h"
#include "libavfilter/buffersrc.h"

#pragma comment(lib, "avcodec.lib")
#pragma comment(lib, "avformat.lib")
#pragma comment(lib, "avutil.lib")
#pragma comment(lib, "avdevice.lib")
#pragma comment(lib, "avfilter.lib")

	//#pragma comment(lib, "avfilter.lib")
	//#pragma comment(lib, "postproc.lib")
#pragma comment(lib, "swresample.lib")
#pragma comment(lib, "swscale.lib")
#ifdef __cplusplus
};
#endif




AVFormatContext	*pFormatCtx_Audio = NULL;
AVFormatContext	*pFormatCtx_AudioMic = NULL;
AVFormatContext *pFormatCtx_Out = NULL;

AVCodecContext *pReadCodecContext = NULL;
AVCodecContext *pReadMicCodecContext = NULL;

int AudioIndex = 0;

AVCodecContext	*pCodecEncodeCtx_Audio = NULL;
AVCodec			*pCodecEncode_Audio = NULL;


AVAudioFifo		*fifo_audio = NULL;
AVAudioFifo		*fifo_audio_mic = NULL;

SwrContext *audio_convert_ctx = NULL;

uint8_t *picture_buf = NULL, *frame_buf = NULL;

bool bCap = true;

int AudioFrameIndex = 0;
int AudioMicFrameIndex = 0;


int64_t cur_pts_a = 0;
int64_t cur_pts_a_mic = 0;



AVFilterGraph* _filter_graph = NULL;
AVFilterContext* _filter_ctx_src_inner = NULL;
AVFilterContext* _filter_ctx_src_mic = NULL;
AVFilterContext* _filter_ctx_sink = NULL;



CRITICAL_SECTION AudioSection;
CRITICAL_SECTION AudioSection_mic;


DWORD WINAPI AudioCapThreadProc(LPVOID lpParam);
DWORD WINAPI AudioMicCapThreadProc(LPVOID lpParam);


typedef struct BufferSourceContext {
   
   
	const AVClass    *bscclass;
	AVFifoBuffer     *fifo;
	AVRational        time_base;     ///< time_base to set in the output link
	AVRational        frame_rate;    ///< frame_rate to set in the output link
	unsigned          nb_failed_requests;
	unsigned          warning_limit;

	/* video only */
	int               w, h;
	enum AVPixelFormat  pix_fmt;
	AVRational        pixel_aspect;
	char              *sws_param;

	AVBufferRef *hw_frames_ctx;

	/* audio only */
	int sample_rate;
	enum AVSampleFormat sample_fmt;
	int channels;
	uint64_t channel_layout;
	char    *channel_layout_str;

	int got_format_from_params;
	int eof;
} BufferSourceContext;



static char *dup_wchar_to_utf8(const wchar_t *w)
{
   
   
	char *s = NULL;
	int l = WideCharToMultiByte(CP_UTF8, 0, w, -1, 0, 0, 0, 0);
	s = (char *)av_malloc(l);
	if (s)
		WideCharToMultiByte(CP_UTF8, 0, w, -1, s, l, 0, 0);
	return s;
}


/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec)
{
   
   
	const int *p;
	int best_samplerate = 0;

	if (!codec->supported_samplerates)
		return 44100;

	p = codec->supported_samplerates;
	while (*p) {
   
   
		if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
			best_samplerate = *p;
		p++;
	}
	return best_samplerate;
}




/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec)
{
   
   
	const uint64_t *p;
	uint64_t best_ch_layout = 0;
	int best_nb_channels = 0;

	if (!codec->channel_layouts)
		return AV_CH_LAYOUT_STEREO;

	p = codec->channel_layouts;
	while (*p) {
   
   
		int nb_channels = av_get_channel_layout_nb_channels(*p);

		if (nb_channels > best_nb_channels) {
   
   
			best_ch_layout = *p;
			best_nb_channels = nb_channels;
		}
		p++;
	}
	return best_ch_layout;
}


int InitFilter(const char* filter_desc)
{
   
   
	char args_inner[512];
	const char* pad_name_inner = "in0";
	char args_mic[512];
	const char