FFmpegPCM播转AAC

要将PCM数据编码为AAC的格式，首先了解一下什么是PCM数据，所谓PCM数据就是未被压缩的音频原始数据，而aac,mp3等都是被有损压缩后的数据。未被压缩的pcm数据所占用的储存空间比较大，而被压缩后的PCM数据所占用的空间会比较小，下面我们看一下所需要设置的压缩参数。

  1. sample_rate : 采样率，也就是每秒采集多少次声音样本

  2. channels : 声道的数目，有单通道和双通道

  3. sample_fmt : 采样的格式

  4. channel_layout: 声道布局

5.bit_rate : 比特率

需要将这些数据为AVCodecContext设置。

主要流程如下：

1.初始化输出环境：

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
AVFormatContext *ofmt_ctx = avformat_alloc_context();
  AVOutputFormat *oformat = av_guess_format(NULL,output,NULL);
  if (oformat==NULL){
    av_log(NULL,AV_LOG_ERROR,"fail to find the output format\n");
    return -1;
  }
  if (avformat_alloc_output_context2(&ofmt_ctx,oformat,oformat->name,output) <0){
    av_log(NULL,AV_LOG_ERROR,"fail to alloc output context\n");
    return -1;
  }
  AVStream *out_stream = avformat_new_stream(ofmt_ctx,NULL);
  if (out_stream == NULL){
    av_log(NULL,AV_LOG_ERROR,"fail to create new stream\n");
    return -1;
  }

2.设置AAC编码格式：

1
2
3
4
5
6
7
8
AVCodecContext *pCodecCtx = out_stream->codec;
 pCodecCtx->codec_id = oformat->audio_codec;
 pCodecCtx->codec_type = AVMEDIA_TYPE_AUDIO;
 pCodecCtx->sample_fmt = AV_SAMPLE_FMT_FLTP; //其他会出错
 pCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
 pCodecCtx->channels = av_get_channel_layout_nb_channels(pCodecCtx->channel_layout);
 pCodecCtx->sample_rate = 44100;
 pCodecCtx->bit_rate = 128000;

3.打开编码器并向输出文件中写入文件头信息

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
AVCodec *pCodec = avcodec_find_encoder(pCodecCtx->codec_id);
if (pCodec == NULL){
  av_log(NULL,AV_LOG_ERROR,"fail to find codec\n");
  return -1;
}
if (avcodec_open2(pCodecCtx,pCodec,NULL) < 0){
  av_log(NULL,AV_LOG_ERROR,"fail to open codec\n");
  return -1;
}
av_dump_format(ofmt_ctx,0,output,1);
if (avio_open(&ofmt_ctx->pb,output,AVIO_FLAG_WRITE) < 0){
  av_log(NULL,AV_LOG_ERROR,"fail to open output\n");
  return -1;
}
if (avformat_write_header(ofmt_ctx,NULL) < 0){
  av_log(NULL,AV_LOG_ERROR,"fail to write header");
  return -1;
}

4.设置一些参数，需要将pcm raw data压缩为aac格式

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
AVFrame *pframe = av_frame_alloc();
 pframe->channels = pCodecCtx->channels;
 pframe->format = pCodecCtx->sample_fmt;
 pframe->nb_samples = pCodecCtx->frame_size;
 //从文件中读取原始数据，缓冲区
 int size = av_samples_get_buffer_size(NULL,pCodecCtx->channels,pCodecCtx->frame_size,pCodecCtx->sample_fmt,1);
 uint8_t *out_buffer = (uint8_t*)av_malloc(size);
 avcodec_fill_audio_frame(pframe,pCodecCtx->channels,pCodecCtx->sample_fmt,(const uint8_t*)out_buffer,size,1);

 //新版本需要使用到转换参数，将读取的数据转换成输出的编码格式
 uint8_t  **data = (uint8_t**)av_calloc( pCodecCtx->channels,sizeof(*data) );
 av_samples_alloc(data,NULL,pCodecCtx->channels,pCodecCtx->frame_size,pCodecCtx->sample_fmt,1);

 SwrContext *pSwrCtx  = swr_alloc();
 swr_alloc_set_opts(pSwrCtx,pCodecCtx->channel_layout,pCodecCtx->sample_fmt,pCodecCtx->sample_rate,
     pCodecCtx->channel_layout,AV_SAMPLE_FMT_S16,44100,0,NULL);
 swr_init(pSwrCtx);
 //需要使用AVPacket进行压缩储存
 AVPacket *pkt = av_packet_alloc();
 av_new_packet(pkt,size);
 pkt->data = NULL;
 pkt->size = 0;

5.读取pcm raw data并压缩为aac格式的数据写入输出文件中

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
int count = 1;
  while(1){
    //读取的长度要 和原始数据的采样率，采样格式以及通道有关 如果size设置的不对，会导致音频错误
    size = pframe->nb_samples * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * pframe->channels;
    if (fread(out_buffer,1,size,fp) < 0){
      printf("fail to read raw data\n");
      return -1;
    }else if (feof(fp)){
      break;
    }

    swr_convert(pSwrCtx,data,pCodecCtx->frame_size,pframe->data,pframe->nb_samples);
    //转换后的数据大小与采样率和采样格式有关
    size = pCodecCtx->frame_size * av_get_bytes_per_sample(pCodecCtx->sample_fmt);
    memcpy(pframe->data[0],data[0],size);
    memcpy(pframe->data[1],data[1],size);
    pframe->pts = count * 100;
    //编码写入
    if (avcodec_send_frame(pCodecCtx,pframe) < 0){
      printf("fail to send frame\n");
      return -1;
    }
    //读取编码好的数据
    if (avcodec_receive_packet(pCodecCtx,pkt)  >= 0){
      pkt->stream_index = out_stream->index;
      av_log(NULL,AV_LOG_INFO,"write %d frame\n",count);
      av_write_frame(ofmt_ctx,pkt);
    }
    count++;
    av_packet_unref(pkt);
  }
  1. 刷新编码器，将编码器中的数据写入到文件中
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
int flush_encoder(AVFormatContext *ofmt_ctx,int stream_index){
  if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities & AV_CODEC_CAP_DELAY)){
    return 0;
  }
  int got_fame = 0;
  AVPacket *pkt = av_packet_alloc();

  while(1)
  {
    pkt->data = NULL;
    pkt->size = 0;
    av_init_packet(pkt);
    int ret = avcodec_encode_audio2(ofmt_ctx->streams[stream_index]->codec,pkt,NULL,&got_fame);
    if (ret < 0){
      break;
    }
    if (got_fame == 0){
      break;
    }
    //mux the frame data
    ret = av_write_frame(ofmt_ctx,pkt);
    if (ret < 0){
      break;
    }
  }
  av_packet_free(&pkt);
  return 0;
}

7.写入文件尾部信息

1
av_write_trailer(ofmt_ctx);

8.释放所有申请的资源

1
2
3
4
5
6
7
av_packet_free(&pkt);
swr_free(&pSwrCtx);
av_free(out_buffer);
av_frame_free(&pframe);

avio_close(ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);

完整代码实现如下：

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
#include <stdio.h>
#include <stdlib.h>
#include <libavformat/avformat.h>
#include <libavcodec/avcodec.h>
#include <libswresample/swresample.h>
int flush_encoder(AVFormatContext *ofmt_ctx,int stream_index){
  if (!(ofmt_ctx->streams[stream_index]->codec->codec->capabilities & AV_CODEC_CAP_DELAY)){
    return 0;
  }
  int got_fame = 0;
  AVPacket *pkt = av_packet_alloc();

  while(1)
  {
    pkt->data = NULL;
    pkt->size = 0;
    av_init_packet(pkt);
    int ret = avcodec_encode_audio2(ofmt_ctx->streams[stream_index]->codec,pkt,NULL,&got_fame);
    if (ret < 0){
      break;
    }
    if (got_fame == 0){
      break;
    }
    ret = av_write_frame(ofmt_ctx,pkt);
    if (ret < 0){
      break;
    }
  }
  av_packet_free(&pkt);
  return 0;
}
int main(int argc,char *argv[])
{
  if (argc != 3){
    printf("usage : Encode <input pcm data> <output aac>");
    return -1;
  }
  const char *input = argv[1];
  const char *output = argv[2];
  av_register_all();
  AVFormatContext *ofmt_ctx = avformat_alloc_context();
  AVOutputFormat *oformat = av_guess_format(NULL,output,NULL);
  if (oformat==NULL){
    av_log(NULL,AV_LOG_ERROR,"fail to find the output format\n");
    return -1;
  }
  if (avformat_alloc_output_context2(&ofmt_ctx,oformat,oformat->name,output) <0){
    av_log(NULL,AV_LOG_ERROR,"fail to alloc output context\n");
    return -1;
  }
  AVStream *out_stream = avformat_new_stream(ofmt_ctx,NULL);
  if (out_stream == NULL){
    av_log(NULL,AV_LOG_ERROR,"fail to create new stream\n");
    return -1;
  }
  AVCodecContext *pCodecCtx = out_stream->codec;
  pCodecCtx->codec_id = oformat->audio_codec;
  pCodecCtx->codec_type = AVMEDIA_TYPE_AUDIO;
  pCodecCtx->sample_fmt = AV_SAMPLE_FMT_FLTP; //其他会出错
  pCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
  pCodecCtx->channels = av_get_channel_layout_nb_channels(pCodecCtx->channel_layout);
  pCodecCtx->sample_rate = 44100;
  pCodecCtx->bit_rate = 128000;

  AVCodec *pCodec = avcodec_find_encoder(pCodecCtx->codec_id);
  if (pCodec == NULL){
    av_log(NULL,AV_LOG_ERROR,"fail to find codec\n");
    return -1;
  }
  if (avcodec_open2(pCodecCtx,pCodec,NULL) < 0){
    av_log(NULL,AV_LOG_ERROR,"fail to open codec\n");
    return -1;
  }
  av_dump_format(ofmt_ctx,0,output,1);
  if (avio_open(&ofmt_ctx->pb,output,AVIO_FLAG_WRITE) < 0){
    av_log(NULL,AV_LOG_ERROR,"fail to open output\n");
    return -1;
  }
  if (avformat_write_header(ofmt_ctx,NULL) < 0){
    av_log(NULL,AV_LOG_ERROR,"fail to write header");
    return -1;
  }
  FILE *fp = fopen(input,"rb");
  if(fp == NULL){
    printf("fail to open file\n");
    return -1;
  }
  AVFrame *pframe = av_frame_alloc();
  pframe->channels = pCodecCtx->channels;
  pframe->format = pCodecCtx->sample_fmt;
  pframe->nb_samples = pCodecCtx->frame_size;

  int size = av_samples_get_buffer_size(NULL,pCodecCtx->channels,pCodecCtx->frame_size,pCodecCtx->sample_fmt,1);
  uint8_t *out_buffer = (uint8_t*)av_malloc(size);
  avcodec_fill_audio_frame(pframe,pCodecCtx->channels,pCodecCtx->sample_fmt,(const uint8_t*)out_buffer,size,1);

  //新版本需要使用到转换参数，将读取的数据转换成输出的编码格式
  uint8_t  **data = (uint8_t**)av_calloc( pCodecCtx->channels,sizeof(*data) );
  av_samples_alloc(data,NULL,pCodecCtx->channels,pCodecCtx->frame_size,pCodecCtx->sample_fmt,1);

  SwrContext *pSwrCtx  = swr_alloc();
  swr_alloc_set_opts(pSwrCtx,pCodecCtx->channel_layout,pCodecCtx->sample_fmt,pCodecCtx->sample_rate,
      pCodecCtx->channel_layout,AV_SAMPLE_FMT_S16,44100,0,NULL);
  swr_init(pSwrCtx);
  AVPacket *pkt = av_packet_alloc();
  av_new_packet(pkt,size);
  pkt->data = NULL;
  pkt->size = 0;

  int count = 1;
  while(1){
    //读取的长度要 和原始数据的采样率，采样格式以及通道有关 如果size设置的不对，会导致音频错误
    size = pframe->nb_samples * av_get_bytes_per_sample(AV_SAMPLE_FMT_S16) * pframe->channels;
    if (fread(out_buffer,1,size,fp) < 0){
      printf("fail to read raw data\n");
      return -1;
    }else if (feof(fp)){
      break;
    }
    
    swr_convert(pSwrCtx,data,pCodecCtx->frame_size,pframe->data,pframe->nb_samples);
    //转换后的数据大小与采样率和采样格式有关
    size = pCodecCtx->frame_size * av_get_bytes_per_sample(pCodecCtx->sample_fmt);
    memcpy(pframe->data[0],data[0],size);
    memcpy(pframe->data[1],data[1],size);
    pframe->pts = count * 100;
    //编码写入
    if (avcodec_send_frame(pCodecCtx,pframe) < 0){
      printf("fail to send frame\n");
      return -1;
    }
    //读取编码好的数据
    if (avcodec_receive_packet(pCodecCtx,pkt)  >= 0){
      pkt->stream_index = out_stream->index;
      av_log(NULL,AV_LOG_INFO,"write %d frame\n",count);
      av_write_frame(ofmt_ctx,pkt);
    }
    count++;
    av_packet_unref(pkt);
  }
  //刷新编码器的缓冲区
  flush_encoder(ofmt_ctx,out_stream->index);

  av_packet_free(&pkt);
  swr_free(&pSwrCtx);
  av_free(out_buffer);
  av_frame_free(&pframe);
  av_write_trailer(ofmt_ctx);
  avio_close(ofmt_ctx->pb);
  avformat_free_context(ofmt_ctx);
  return 0;
}

当我使用此代码将pcm转换到mp3的时候会出错，可能是我自己编译的ffmpeg有问题，不支持mp3格式的压缩。

赏

谢谢你请我吃糖果

扫一扫，分享到微信

微信分享二维码

tag:

    缺失模块。
    1、请确保node版本大于6.2
    2、在博客根目录（注意不是yilia根目录）执行以下命令：
    npm i hexo-generator-json-content --save

    3、在根目录_config.yml里添加配置： 

      jsonContent:
    meta: false
    pages: false
    posts:
      title: true
      date: true
      path: true
      text: false
      raw: false
      content: false
      slug: false
      updated: false
      comments: false
      link: false
      permalink: false
      excerpt: false
      categories: false
      tags: true

I am what I am