FFmpeg 示例音频编码

目录

1. 参考
2. 示例说明
3. 示例代码

1. 参考

• [1] FFmpeg/doc/examples/encode_audio.c
• [2] FFmpeg 文档：send/receive encoding and decoding API overview

2. 示例说明

示例来源于[1]，把PCM数据编码为MP2格式的数据。

示例的流程如下所示。

FFmpeg_encode_audio.png

关键函数说明：

• avcodec_find_encoder：根据指定的AVCodecID查找注册的解码器。
• avcodec_alloc_context3：为AVCodecContext分配内存。
• avcodec_open2：打开解码器。
• avcodec_send_frame：将AVFrame非压缩数据给编码器。详细介绍见FFmpeg音频解码的编解码API介绍部分。
• avcodec_receive_packet：获取到编码后的AVPacket数据。
• av_frame_get_buffer: 为音频或视频数据分配新的buffer。在调用这个函数之前，必须在AVFame上设置好以下属性：format(视频为像素格式，音频为样本格式)、nb_samples(样本个数，针对音频)、channel_layout(通道类型，针对音频)、width/height(宽高，针对视频）。
• av_frame_make_writable：确保AVFrame是可写的，尽可能避免数据的复制。
  如果AVFrame不是是可写的，将分配新的buffer和复制数据。

3. 示例代码

/**
 * @file
 * audio encoding with libavcodec API example.
 *
 * @example encode_audio.c
 */

#include 
#include 
#include 

#include 

#include 
#include 
#include 
#include 

/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec, enum AVSampleFormat sample_fmt)
{
    const enum AVSampleFormat *p = codec->sample_fmts;

    while (*p != AV_SAMPLE_FMT_NONE) {
        if (*p == sample_fmt)
            return 1;
        p++;
    }
    return 0;
}

/* 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;
}

static void encode(AVCodecContext *ctx, AVFrame *frame, AVPacket *pkt,
                   FILE *output)
{
    int ret;

    /* send the frame for encoding */
    ret = avcodec_send_frame(ctx, frame);
    if (ret < 0) {
        fprintf(stderr, "Error sending the frame to the encoder\n");
        exit(1);
    }

    /* read all the available output packets (in general there may be any
     * number of them */
    while (ret >= 0) {
        ret = avcodec_receive_packet(ctx, pkt);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error encoding audio frame\n");
            exit(1);
        }

        fwrite(pkt->data, 1, pkt->size, output);
        av_packet_unref(pkt);
    }
}

int main(int argc, char **argv)
{
    const char *filename;
    const AVCodec *codec;
    AVCodecContext *c= NULL;
    AVFrame *frame;
    AVPacket *pkt;
    int i, j, k, ret;
    FILE *f;
    uint16_t *samples;
    float t, tincr;

    if (argc <= 1) {
        fprintf(stderr, "Usage: %s 
\n", argv[0]);
        return 0;
    }
    filename = argv[1];

    /* find the MP2 encoder */
    codec = avcodec_find_encoder(AV_CODEC_ID_MP2);
    if (!codec) {
        fprintf(stderr, "Codec not found\n");
        exit(1);
    }

    c = avcodec_alloc_context3(codec);
    if (!c) {
        fprintf(stderr, "Could not allocate audio codec context\n");
        exit(1);
    }

    /* put sample parameters */
    c->bit_rate = 64000;

    /* check that the encoder supports s16 pcm input */
    c->sample_fmt = AV_SAMPLE_FMT_S16;
    if (!check_sample_fmt(codec, c->sample_fmt)) {
        fprintf(stderr, "Encoder does not support sample format %s",
                av_get_sample_fmt_name(c->sample_fmt));
        exit(1);
    }

    /* select other audio parameters supported by the encoder */
    c->sample_rate    = select_sample_rate(codec);
    c->channel_layout = select_channel_layout(codec);
    c->channels       = av_get_channel_layout_nb_channels(c->channel_layout);

    /* open it */
    if (avcodec_open2(c, codec, NULL) < 0) {
        fprintf(stderr, "Could not open codec\n");
        exit(1);
    }

    f = fopen(filename, "wb");
    if (!f) {
        fprintf(stderr, "Could not open %s\n", filename);
        exit(1);
    }

    /* packet for holding encoded output */
    pkt = av_packet_alloc();
    if (!pkt) {
        fprintf(stderr, "could not allocate the packet\n");
        exit(1);
    }

    /* frame containing input raw audio */
    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Could not allocate audio frame\n");
        exit(1);
    }

    frame->nb_samples     = c->frame_size;
    frame->format         = c->sample_fmt;
    frame->channel_layout = c->channel_layout;

    /* allocate the data buffers */
    ret = av_frame_get_buffer(frame, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not allocate audio data buffers\n");
        exit(1);
    }

    /* encode a single tone sound */
    t = 0;
    tincr = 2 * M_PI * 440.0 / c->sample_rate;
    for (i = 0; i < 200; i++) {
        /* make sure the frame is writable -- makes a copy if the encoder
         * kept a reference internally */
        ret = av_frame_make_writable(frame);
        if (ret < 0)
            exit(1);
        samples = (uint16_t*)frame->data[0];

        for (j = 0; j < c->frame_size; j++) {
            samples[2*j] = (int)(sin(t) * 10000);

            for (k = 1; k < c->channels; k++)
                samples[2*j + k] = samples[2*j];
            t += tincr;
        }
        encode(c, frame, pkt, f);
    }

    /* flush the encoder */
    encode(c, NULL, pkt, f);

    fclose(f);

    av_frame_free(&frame);
    av_packet_free(&pkt);
    avcodec_free_context(&c);

    return 0;
}

说明：

1. 示例中PCM的样本格式为AV_SAMPLE_FMT_S16，为packed格式，各通道数据交错存储的。