树莓派sip视频电话-2：alsa+g711+rtp传输音频

最新推荐文章于 2025-05-07 13:40:41 发布

aphero

最新推荐文章于 2025-05-07 13:40:41 发布

阅读量6.5k

点赞数 1

分类专栏：树莓派

树莓派专栏收录该内容

15 篇文章

订阅专栏

本文介绍了一种在树莓派上实现音频采集、G711编码及通过RTP协议传输的方法。该方案利用USB摄像头自带麦克风进行录音，并通过自定义程序完成编码与网络传输，适用于远程音频通话应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

前面在树莓派上已经实现了视频硬件编码传输，但是声音却一直找不到好的方法，只能自己写代码实现。

程序说明：

1.alsa录音部分：

树莓派上使用的是usb的摄像头自带麦克，所以采集的声卡是“hw:1,0”, default未试。这里一定要注意的是采样频率，period_time，buffer_time等参数设置，因为rtp传输使用的是160的时间戳增量，必须采集后的size为320字节（g711编码后数据量减少一半，刚好为160字节）。

程序demo中有三种输出方式：1是保存pcm文件；2是保存g711文件；3是g711经rtp传输。

三种方式播放测试方法：网上都没有介绍的，需安装sox sudo apt-get install sox

（1）.播放pcm文件

play -t s16 -r 8000 -c 1 -e signed-integer dest.pcm 

dest.pcm:

 File Size: 4.81M     Bit Rate: 128k
  Encoding: Signed PCM    
  Channels: 1 @ 16-bit   
Samplerate: 8000Hz       
Replaygain: off         
  Duration: 00:05:00.42

（2）.播放g711文件：

play -t raw -r 8000 -c 1  -e a-law test.g711

test.g711:

 File Size: 2.40M     Bit Rate: 64.0k
  Encoding: A-law         
  Channels: 1 @ 13-bit   
Samplerate: 8000Hz       
Replaygain: off         
  Duration: 00:05:00.42

（3）.播放rtp视频流

vlc播放sdp文件实现

m=audio 5100 RTP/AVP 0  
a=rtpmap:0 pcma/8000/1  
a=ptime:20
c=IN IP4 192.168.1.132

2.G711编码部分：

G711编码有a和u两种编码方式，在程序中已经实现了接口，直接调用就可以了。网上借鉴别人代码（github）。

3.RTP传输部分：

没有使用库文件，直接实现。使用160时间戳增量，rtp发送数据包大小为214字节。

程序demo代码如下：

1.alsa_record.c

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <memory.h>

#include <netdb.h>
#include <time.h>
#include <sys/types.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <unistd.h>    //close()

#include <alsa/asoundlib.h>
#include <math.h>
#include "g711codec.h"


#define DEST_PORT  5100
#define DEST_IP "192.168.1.132"

#define BUFFERSIZE 4096
#define PERIOD_SIZE 1024
#define PERIODS 2
#define SAMPLE_RATE 8000
#define CHANNELS 1
#define FSIZE 2*CHANNELS

/* Use the newer ALSA API */
#define ALSA_PCM_NEW_HW_PARAMS_API


typedef struct
{
    /** byte 0 */
    unsigned char csrc_len:4;        /** expect 0 */
    unsigned char extension:1;       /** expect 1, see RTP_OP below */
    unsigned char padding:1;         /** expect 0 */
    unsigned char version:2;         /** expect 2 */
    /** byte 1 */
    unsigned char payload:7;         /** stream type */
    unsigned char marker:1;          /** when send the first framer,set it */
    /** bytes 2, 3 */
    unsigned short seq_no;
    /** bytes 4-7 */
    unsigned  long timestamp;
    /** bytes 8-11 */
    unsigned long ssrc;              /** stream number is used here. */
} RTP_FIXED_HEADER;


int main(int argc, char *argv[]) {

	long loops; //define the record time.
	int rc;	//return code.
	int size;
	snd_pcm_t *handle;
	snd_pcm_hw_params_t *params;
	unsigned int val;
	int dir;
	snd_pcm_uframes_t frames;
	char *buffer;
 	
	int err;
	char *file;

	int fd;
	int fd2;
	if(argc ==2)
	{
		file = argv[1];
	}
	else
	{
		file = "output.raw";
	}

	fd = open(file,O_WRONLY|O_CREAT,0777);
	if( fd ==-1)
	{
		printf("open file:%s fail.\n",file);
		exit(1);
	}
	fd2 = open("test.g711",O_WRONLY|O_CREAT,0777);
	if( fd ==-1)
	{
		printf("open file:%s fail.\n",file);
		exit(1);
	}

	/* Open PCM device for recording (capture). */
	err = snd_pcm_open(&handle, "default",SND_PCM_STREAM_CAPTURE, 0);
	if (err < 0) {
		fprintf(stderr,"unable to open pcm device: %s\n",snd_strerror(err));
		exit(1);
	}

	/* Allocate a hardware parameters object. */
	snd_pcm_hw_params_alloca(¶ms);

	/* Fill it in with default values. */
	err=snd_pcm_hw_params_any(handle, params);
		if (err < 0) {
		    fprintf(stderr, "Can not configure this PCM device: %s\n",snd_strerror(err));
		    exit(1);
		}
	/* Set the desired hardware parameters. */

	/* Interleaved mode */
	err=snd_pcm_hw_params_set_access(handle, params,SND_PCM_ACCESS_RW_INTERLEAVED);
		if (err < 0) {
		    fprintf(stderr,   "Failed to set PCM device to interleaved: %s\n", snd_strerror(err));
		    exit(1);
		}
	/* Signed 16-bit little-endian format */
	//err=snd_pcm_hw_params_set_format(handle, params,SND_PCM_FORMAT_MU_LAW);
	err=snd_pcm_hw_params_set_format(handle, params,SND_PCM_FORMAT_S16_LE);
		if (err < 0) {
		    fprintf(stderr,"Failed to set PCM device to 16-bit signed PCM: %s\n", snd_strerror(err));
		    exit(1);
		}
	/* One channels (mono) */
	err=snd_pcm_hw_params_set_channels(handle, params, CHANNELS);
		if (err < 0) {
		    fprintf(stderr, "Failed to set PCM device to mono: %s\n",snd_strerror(err));
		    exit(1);
		}
	/* 16000 bits/second sampling rate (CD quality) */
	val = SAMPLE_RATE;//这里修改为8000
	err=snd_pcm_hw_params_set_rate_near(handle, params,&val, &dir);
		if (err < 0) {
		    fprintf(stderr, "Failed to set PCM device to sample rate =%d: %s\n",val,snd_strerror(err));
		    exit(1);
		}

	/* Set buffer time 500000. */
	unsigned int buffer_time,period_time;
	snd_pcm_hw_params_get_buffer_time_max(params, &buffer_time, 0);
	if ( buffer_time >500000) 		
	buffer_time = 80000;//这里可修改
	//period_time = buffer_time / 4;
	period_time = buffer_time/4;//这里可修改  size = frames * FSIZE;
	err = snd_pcm_hw_params_set_buffer_time_near(handle, params, &buffer_time, 0);
		if (err < 0) {
		    fprintf(stderr, "Failed to set PCM device to buffer time =%d: %s\n",  buffer_time,snd_strerror(err));
		    exit(1);
		}

	err = snd_pcm_hw_params_set_period_time_near(handle, params, &period_time, 0);
		if (err < 0) {
		    fprintf(stderr, "Failed to set PCM device to period time =%d: %s\n",period_time,snd_strerror(err));
		    exit(1);
		}


	/* Write the parameters to the driver */
	err = snd_pcm_hw_params(handle, params);
		if (err < 0) {
			fprintf(stderr,"unable to set hw parameters: %s\n",snd_strerror(err));
			exit(1);
		}

	/* Use a buffer large enough to hold one period */
	snd_pcm_hw_params_get_period_size(params,&frames, &dir);
	size = frames * FSIZE; /* 2 bytes/sample, 1 channels *///这里应该=320  FSIZE=2    frames=160
	buffer = (char *) malloc(size);
	
	printf("read buffer size = %d\n",size);
	printf("period size = %d frames\n", (int)frames);



	/* We want to loop for 5 seconds */
	snd_pcm_hw_params_get_period_time(params,&val, &dir);
	printf("period time is: %d\n",val);
	

	/*print alsa config parameter*/

	snd_pcm_hw_params_get_buffer_time(params, &val, &dir);
	printf("buffer time = %d us\n", val);

	snd_pcm_hw_params_get_buffer_size(params, (snd_pcm_uframes_t *) &val);
	printf("buffer size = %d frames\n", val);

	snd_pcm_hw_params_get_periods(params, &val, &dir);
	printf("periods per buffer = %d frames\n", val);
	
	//-----------------------------------rtp初始化部分--开始------------------------------------------------------

	//int ret;
    int M_bit;
    M_bit = 1;

    char sendbuf[1500];
    memset(sendbuf,0,1500);
    unsigned short seq_num = 0;
    RTP_FIXED_HEADER        *rtp_hdr;

    int    socket1;
    struct sockaddr_in server;
    int len = sizeof(server);
    //float framerate = 25;
    unsigned int timestamp_increse = 0,ts_current = 0;
    timestamp_increse = 160;

    server.sin_family = AF_INET;
    server.sin_port = htons(DEST_PORT);
    server.sin_addr.s_addr = inet_addr(DEST_IP);
    socket1 = socket(AF_INET,SOCK_DGRAM,0);
    connect(socket1, (struct sockaddr *)&server, len);

//----------------------------------------------rtp初始化部分 -----结束--------------------------------------------
loops = 1000;
	while (1) {
		loops--;

		rc = snd_pcm_readi(handle, buffer, frames);

		if (rc == -EPIPE) {
		// EPIPE means overrun 
			fprintf(stderr, "overrun occurred\n");
			err=snd_pcm_prepare(handle);
			if( err <0){
				fprintf(stderr, "Failed to recover form overrun : %s\n",
				snd_strerror(err));
				exit(1);
			}
		}
		else if (rc < 0) {
			fprintf(stderr,"error from read: %s\n",snd_strerror(rc));
			exit(1);
		} 
		else if (rc != (int)frames) {
			fprintf(stderr, "short read, read %d frames\n", rc);
		
		}
		rc = write(fd, buffer, size);
		if (rc <0){
			perror("fail to write to audio file\n");
		}
//#-------------------------------------------------------------------------------------------#		
	
	
		int Ret = -1;
		unsigned char ucOutBuff[1024 + 1 ];
		memset(ucOutBuff, 0, sizeof(ucOutBuff));
		Ret = PCM2G711a( (char *)buffer, (char *)ucOutBuff, size, 0 );
		//printf("***************g711 start*******************\n");
		
		rc = PCM2G711a( (char *)buffer, (char *)&sendbuf[12], size, 0 );
		printf("loops=%d,Ret=%d,size=%d\n",(int)loops,rc,size);


		rtp_hdr =(RTP_FIXED_HEADER*)&sendbuf[0];
	//设置RTP HEADER，
	rtp_hdr->payload     = 0;  //负载类型号，
	rtp_hdr->version     = 2;  //版本号，此版本固定为2
		if(1 == M_bit)
		{
		    rtp_hdr->marker    = 1;   //标志位，由具体协议规定其值。
		    M_bit = 0;
		    printf("M_bit = 1\n");
		}
		else
		{
		    rtp_hdr->marker    = 0;   //标志位，由具体协议规定其值。
		}

	rtp_hdr->ssrc        = htonl(10);    //随机指定为10，并且在本RTP会话中全局唯一

	rtp_hdr->seq_no = htons(seq_num ++);
	//printf("sendbuf[1]=%x\n",sendbuf[1]);
	ts_current = ts_current+timestamp_increse;
	//printf("ts_current=%d\n",ts_current);
	rtp_hdr->timestamp=htonl(ts_current);
	//printf("calloc\n");



	rc = send( socket1, sendbuf, rc+12, 0 );//发送rtp包
	//printf("send:%d\n",rc);//=rc+12
        if(rc<0)
      		  {
            perror("send");
            break;
        	}
/**
       
        printf("***************rtp*******************\n");
        printf("ret = %d\n",rc);
        printf("rtp_hdr->payload = %x\n",rtp_hdr->payload);
        printf("rtp_hdr->version = %x\n",rtp_hdr->version);
        printf("rtp_hdr->marker = %x\n",rtp_hdr->marker);
        printf("rtp_hdr->ssrc = %x\n",(unsigned int)rtp_hdr->ssrc);
        printf("rtp_hdr->seq_no = %x\n",rtp_hdr->seq_no);
        printf("rtp_hdr->timestamp = %x\n",(unsigned int)rtp_hdr->timestamp);
        printf("sendbuf[0]= %x\n",sendbuf[0]);
        printf("sendbuf[12]= %x\n",sendbuf[12]);
        printf("**********************************\n");
*/
	    //usleep(19000);
        memset(sendbuf,0,1500);//清空sendbuf；此时会将上次的时间戳清空，因此需要ts_current来保存上次的时间戳值
		


//#-------------------------------------------------------------------------------------------#		

		Ret = write(fd2, &ucOutBuff, Ret);
		if (Ret <0){
			perror("fail to write to audio file\n");
		}

	}

	close(fd);
	//close(fd2);
	snd_pcm_drain(handle);
	snd_pcm_close(handle);
	free(buffer);

	return 0;
}

2.g711codec.h

/*
 * G711 encode decode HEADER.
 */

#ifndef	__G711CODEC_H__
#define	__G711CODEC_H__

/*
* u-law, A-law and linear PCM conversions.
*/
#define	SIGN_BIT	(0x80)		/* Sign bit for a A-law byte. */
#define	QUANT_MASK	(0xf)		/* Quantization field mask. */
#define	NSEGS		(8)			/* Number of A-law segments. */
#define	SEG_SHIFT	(4)			/* Left shift for segment number. */
#define	SEG_MASK	(0x70)		/* Segment field mask. */
#define	BIAS		(0x84)		/* Bias for linear code. */

int PCM2G711a( char *InAudioData, char *OutAudioData, int DataLen, int reserve );
int PCM2G711u( char *InAudioData, char *OutAudioData, int DataLen, int reserve );

int G711a2PCM( char *InAudioData, char *OutAudioData, int DataLen, int reserve );
int G711u2PCM( char *InAudioData, char *OutAudioData, int DataLen, int reserve );

int g711a_decode(short amp[], const unsigned char g711a_data[], int g711a_bytes);

int g711u_decode(short amp[], const unsigned char g711u_data[], int g711u_bytes);

int g711a_encode(unsigned char g711_data[], const short amp[], int len);

int g711u_encode(unsigned char g711_data[], const short amp[], int len);

#endif  /* g711codec.h */

3.g711.c

#include <stdio.h>
#include "g711codec.h"

/*
 * function: convert PCM audio format to g711 alaw/ulaw.(zqj)
 *	 InAudioData:	PCM data prepared for encoding to g711 alaw/ulaw.
 *   OutAudioData:	encoded g711 alaw/ulaw.
 *   DataLen:		PCM data size.
 *   reserve:		reserved param, no use.
 */

/*alaw*/
int PCM2G711a( char *InAudioData, char *OutAudioData, int DataLen, int reserve )
{	
	//check params.
	if( (NULL == InAudioData) && (NULL == OutAudioData) && (0 == DataLen) )
	{
		printf("Error, empty data or transmit failed, exit !\n");	
		return -1;
	}
	//printf("DataLen = %d, %s, %d\n", DataLen, __func__, __LINE__);

	int Retaen = 0; 
	//printf("G711a encode start......\n");
	Retaen = g711a_encode( (unsigned char *)OutAudioData, (short*)InAudioData, DataLen/2 );
	//printf("Retaen = %d, %s, %d\n", Retaen, __func__, __LINE__);

	return Retaen; //index successfully encoded data len.
}

/*ulaw*/
int PCM2G711u( char *InAudioData, char *OutAudioData, int DataLen, int reserve )
{	
	//check params.
	if( (NULL == InAudioData) && (NULL == OutAudioData) && (0 == DataLen) )
	{
		printf("Error, empty data or transmit failed, exit !\n");	
		return -1;
	}
	printf("DataLen = %d, %s, %d\n", DataLen, __func__, __LINE__);

	int Retuen = 0; 
	printf("G711u encode start......\n");
	Retuen = g711u_encode( (unsigned char *)OutAudioData, (short*)InAudioData, DataLen/2 );
	printf("Retuen = %d, %s, %d\n", Retuen, __func__, __LINE__);

	return Retuen; 
}

/*
 * function: convert g711 alaw audio format to PCM.(zqj)
 *	 InAudioData:	g711 alaw data prepared for encoding to PCM.
 *   OutAudioData:	encoded PCM audio data.
 *   DataLen:		g711a data size.
 *   reserve:		reserved param, no use.
 */

/*alaw*/
int G711a2PCM( char *InAudioData, char *OutAudioData, int DataLen, int reserve )
{
	//check param.
	if( (NULL == InAudioData) && (NULL == OutAudioData) && (0 == DataLen) )
	{
		printf("Error, empty data or transmit failed, exit !\n");	
		return -1;
	}
	printf("DataLen = %d, %s, %d\n", DataLen, __func__, __LINE__);

	int Retade = 0;
	printf("G711a decode start......\n");
	Retade = g711a_decode( (short*)OutAudioData, (unsigned char *)InAudioData, DataLen );
	printf("Retade = %d, %s, %d\n", Retade, __func__, __LINE__);

	return Retade;	//index successfully decoded data len.
}

/*ulaw*/
int G711u2PCM( char *InAudioData, char *OutAudioData, int DataLen, int reserve )
{
	//check param.
	if( (NULL == InAudioData) && (NULL == OutAudioData) && (0 == DataLen) )
	{
		printf("Error, empty data or transmit failed, exit !\n");	
		return -1;
	}
	printf("DataLen = %d, %s, %d\n", DataLen, __func__, __LINE__);

	int Retude = 0;
	printf("G711u decode start......\n");
	Retude = g711u_decode( (short*)OutAudioData, (unsigned char *)InAudioData, DataLen );
	printf("Retude = %d, %s, %d\n", Retude, __func__, __LINE__);

	return Retude;	
}

4.g711codec.c

#include "g711codec.h"

static short seg_end[8] = {0xFF, 0x1FF, 0x3FF, 0x7FF,
			    0xFFF, 0x1FFF, 0x3FFF, 0x7FFF};

static int search(int val, short	*table, int	size)
{
	int	i;

	for (i = 0; i < size; i++) {
		if (val <= *table++)
			return (i);
	}
	return (size);
}

/*
* alaw2linear() - Convert an A-law value to 16-bit linear PCM
*
*/
static int alaw2linear( unsigned char a_val )
{
	int	t;
	int	seg;

	a_val ^= 0x55;

	t = (a_val & QUANT_MASK) << 4;
	seg = ( (unsigned)a_val & SEG_MASK ) >> SEG_SHIFT;
	switch (seg) 
	{
		case 0:
			t += 8;
			break;
		case 1:
			t += 0x108;
			break;
		default:
			t += 0x108;
			t <<= seg - 1;
	}
	return ((a_val & SIGN_BIT) ? t : -t);
}


/*
* ulaw2linear() - Convert a u-law value to 16-bit linear PCM
*
* First, a biased linear code is derived from the code word. An unbiased
* output can then be obtained by subtracting 33 from the biased code.
*
* Note that this function expects to be passed the complement of the
* original code word. This is in keeping with ISDN conventions.
*/
static int ulaw2linear(unsigned char u_val)
{
	int	t;

	/* Complement to obtain normal u-law value. */
	u_val = ~u_val;

	/*
	* Extract and bias the quantization bits. Then
	* shift up by the segment number and subtract out the bias.
	*/
	t = ((u_val & QUANT_MASK) << 3) + BIAS;
	t <<= ((unsigned)u_val & SEG_MASK) >> SEG_SHIFT;

	return ((u_val & SIGN_BIT) ? (BIAS - t) : (t - BIAS));
}


/*
 * linear2alaw() - Convert a 16-bit linear PCM value to 8-bit A-law
 *
 */
unsigned char linear2alaw(int pcm_val)	/* 2's complement (16-bit range) */
{
	int		mask;
	int		seg;
	unsigned char	aval;

	if (pcm_val >= 0) {
		mask = 0xD5;		/* sign (7th) bit = 1 */
	} else {
		mask = 0x55;		/* sign bit = 0 */
		pcm_val = -pcm_val - 8;
	}

	/* Convert the scaled magnitude to segment number. */
	seg = search(pcm_val, seg_end, 8);

	/* Combine the sign, segment, and quantization bits. */

	if (seg >= 8)		/* out of range, return maximum value. */
		return (0x7F ^ mask);
	else {
		aval = seg << SEG_SHIFT;
		if (seg < 2)
			aval |= (pcm_val >> 4) & QUANT_MASK;
		else
			aval |= (pcm_val >> (seg + 3)) & QUANT_MASK;
		return (aval ^ mask);
	}
}


/*
 * linear2ulaw() - Convert a linear PCM value to u-law
 *
 */
unsigned char linear2ulaw(int pcm_val)	/* 2's complement (16-bit range) */
{
	int		mask;
	int		seg;
	unsigned char	uval;

	/* Get the sign and the magnitude of the value. */
	if (pcm_val < 0) {
		pcm_val = BIAS - pcm_val;
		mask = 0x7F;
	} else {
		pcm_val += BIAS;
		mask = 0xFF;
	}

	/* Convert the scaled magnitude to segment number. */
	seg = search(pcm_val, seg_end, 8);

	/*
	 * Combine the sign, segment, quantization bits;
	 * and complement the code word.
	 */
	if (seg >= 8)		/* out of range, return maximum value. */
		return (0x7F ^ mask);
	else {
		uval = (seg << 4) | ((pcm_val >> (seg + 3)) & 0xF);
		return (uval ^ mask);
	}
}


int g711a_decode( short amp[], const unsigned char g711a_data[], int g711a_bytes )
{
	int i;
	int samples;
	unsigned char code;
	int sl;

	for ( samples = i = 0; ; )
	{
		if (i >= g711a_bytes)
			break;
		code = g711a_data[i++];

		sl = alaw2linear( code );

		amp[samples++] = (short) sl;
	}
	return samples*2;
}

int g711u_decode(short amp[], const unsigned char g711u_data[], int g711u_bytes)
{
	int i;
	int samples;
	unsigned char code;
	int sl;

	for (samples = i = 0;;)
	{
		if (i >= g711u_bytes)
			break;
		code = g711u_data[i++];

		sl = ulaw2linear(code);

		amp[samples++] = (short) sl;
	}
	return samples*2;
}

int g711a_encode(unsigned char g711_data[], const short amp[], int len)
{
    int i;

    for (i = 0;  i < len;  i++)
	{
        g711_data[i] = linear2alaw(amp[i]);
    }

    return len;
}

int g711u_encode(unsigned char g711_data[], const short amp[], int len)
{
    int i;

    for (i = 0;  i < len;  i++)
	{
        g711_data[i] = linear2ulaw(amp[i]);
    }

    return len;
}

5.makefile

CC=gcc
CCFLAGS=-g -Wall
LDFLAGS=-lasound
all:recordc play

recordc:alsa_record.c
	$(CC) alsa_record.c g711.c g711codec.c  $(CCFLAGS) $(LDFLAGS) -o recordc

play:alsa_play.c
	$(CC) alsa_play.c $(CCFLAGS) $(LDFLAGS) -o play

clean:
	rm recordc play output.raw test.g711

总结：1.程序还只是实现了声音采集+编码+rtp传输，能够配合python+exosip和pc端ekiga实现声音通话。

2.编码只实现了g711a和g711u两种编码方式，带宽需64kpbs。

3.程序中端口和ip地址是固定的，需修改源代码。

下一步：

1.将音频传输部分，整合到Camkit中，实现音频和视频同时传输。

2.有时间的话，将exosip改为c语音，python需调用视频和音频c语音部分。