FFmpeg 实现从麦克风获取流并通过RTMP推流

使用FFmpeg库实现从麦克风获取流并通过RTMP推流，FFmpeg版本为4.4.2-0。RTMP服务器使用的是SRS，我这边是跑在Ubuntu上的，最好是关闭掉系统防火墙。拉流端使用VLC。如果想要降低延时，请看我另外一篇博客，里面有说降低延时的方法。

Linux上查看麦克风设备命令：

#列出系统中的录音设备
arecord -l

#列出设备的详细信息，比如采样规格等
pactl list sources

再记录下Linux下音频设备名 plughw 和 hw 的区别：

代码如下：

#include <stdio.h>
#include <pthread.h>
#include <unistd.h>
#include <libavdevice/avdevice.h>
#include <libswscale/swscale.h>
#include <libavutil/imgutils.h>
#include <libswresample/swresample.h>
#include <libavutil/fifo.h>

AVFormatContext *out_context = NULL;
AVCodecContext *c = NULL;
struct SwrContext *swr_ctx = NULL;
AVStream *out_stream = NULL;
AVFrame *output_frame = NULL;
int fsize = 0, thread_encode_exit = 0;
AVFifoBuffer *fifo = NULL;
pthread_mutex_t lock;

void *thread_encode(void *);
int main(void)
{
    const char *input_format_name = "alsa";
    const char *device_name = "hw:1,0";
    const char *in_sample_rate = "16000";                     // 采样率
    const char *in_channels = "1";                            // 声道数
    const char *url = "rtmp://192.168.3.230/live/livestream"; // rtmp地址
    int ret = -1;
    int streamid = -1;
    AVDictionary *options = NULL;
    AVInputFormat *fmt = NULL;
    AVFormatContext *in_context = NULL;
    AVCodec *codec = NULL;

    // 注册所有设备
    avdevice_register_all();

    // 查找输入格式
    fmt = av_find_input_format(input_format_name);
    if (!fmt)
    {
        printf("av_find_input_format error");
        return -1;
    }

    // 设置麦克风音频参数
    av_dict_set(&options, "sample_rate", in_sample_rate, 0);
    av_dict_set(&options, "channels", in_channels, 0);

    // 打开输入流并初始化格式上下文
    ret = avformat_open_input(&in_context, device_name, fmt, &options);
    if (ret != 0)
    {
        // 错误的时候释放options，成功的话 avformat_open_input 内部会释放
        av_dict_free(&options);
        printf("avformat_open_input error\n");
        return -1;
    }

    // 查找流信息
    if (avformat_find_stream_info(in_context, 0) < 0)
    {
        printf("avformat_find_stream_info failed\n");
        return -1;
    }

    // 查找音频流索引
    streamid = av_find_best_stream(in_context, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
    if (streamid < 0)
    {
        printf("cannot find audio stream");
        goto end;
    }
    AVStream *stream = in_context->streams[streamid];
    printf("audio stream, sample_rate: %d, channels: %d, format: %s\n",
           stream->codecpar->sample_rate, stream->codecpar->channels,
           av_get_sample_fmt_name((enum AVSampleFormat)stream->codecpar->format));

    // 根据通道数获取默认的通道布局
    int64_t channel_layout = av_get_default_channel_layout(stream->codecpar->channels);
    // 初始化重采样上下文，需要把输入的音频采样格式转换为编码器需要的格式
    swr_ctx = swr_alloc_set_opts(NULL,
                                 channel_layout, AV_SAMPLE_FMT_FLTP, stream->codecpar->sample_rate,
                                 channel_layout, stream->codecpar->format, stream->codecpar->sample_rate,
                                 0, NULL);
    if (!swr_ctx || swr_init(swr_ctx) < 0)
    {
        printf("allocate resampler context failed\n");
        goto end;
    }

    // 分配输出格式上下文
    avformat_alloc_output_context2(&out_context, NULL, "flv", NULL);
    if (!out_context)
    {
        printf("avformat_alloc_output_context2 failed\n");
        goto end;
    }

    // 查找编码器
    codec = avcodec_find_encoder(AV_CODEC_ID_AAC);
    if (!codec)
    {
        printf("Codec not found\n");
        goto end;
    }
    printf("codec name: %s\n", codec->name);

    // 创建新的视频流
    out_stream = avformat_new_stream(out_context, NULL);
    if (!out_stream)
    {
        printf("avformat_new_stream failed\n");
        goto end;
    }

    // 分配编码器上下文
    c = avcodec_alloc_context3(codec);
    if (!c)
    {
        printf("avcodec_alloc_context3 failed\n");
        goto end;
    }

    // 设置编码器参数
    c->codec_id = AV_CODEC_ID_AAC;
    c->codec_type = AVMEDIA_TYPE_AUDIO;
    c->sample_fmt = AV_SAMPLE_FMT_FLTP;
    c->sample_rate = stream->codecpar->sample_rate;
    c->channels = stream->codecpar->channels;
    c->channel_layout = channel_layout;
    c->bit_rate = 64000;
    c->profile = FF_PROFILE_AAC_LOW;
    if (out_context->oformat->flags & AVFMT_GLOBALHEADER)
    {
        printf("set AV_CODEC_FLAG_GLOBAL_HEADER\n");
        c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
    }

    // 打开编码器
    if (avcodec_open2(c, codec, NULL) < 0)
    {
        printf("avcodec_open2 failed\n");
        goto end;
    }

    // 将编码器参数复制到流
    ret = avcodec_parameters_from_context(out_stream->codecpar, c);
    if (ret < 0)
    {
        printf("avcodec_parameters_from_context failed\n");
        goto end;
    }

    // 打开url
    if (!(out_context->oformat->flags & AVFMT_NOFILE))
    {
        ret = avio_open(&out_context->pb, url, AVIO_FLAG_WRITE);
        if (ret < 0)
        {
            printf("avio_open error (errmsg '%s')\n", av_err2str(ret));
            goto end;
        }
    }

    // 写文件头
    ret = avformat_write_header(out_context, NULL);
    if (ret < 0)
    {
        printf("avformat_write_header failed\n");
        goto end;
    }

    output_frame = av_frame_alloc();
    if (!output_frame)
    {
        printf("av_frame_alloc failed\n");
        goto end;
    }
    AVPacket *recv_ptk = av_packet_alloc();
    if (!recv_ptk)
    {
        printf("av_packet_alloc failed\n");
        goto end;
    }

    // 设置帧参数， av_frame_get_buffer 在分配缓冲区时会用到
    output_frame->format = c->sample_fmt;
    output_frame->nb_samples = c->frame_size;
    output_frame->channel_layout = c->channel_layout;

    // 分配缓冲区
    ret = av_frame_get_buffer(output_frame, 0);
    if (ret < 0)
    {
        printf("av_frame_get_buffer failed\n");
        goto end;
    }

    // 计算编码每帧aac所需的pcm数据的大小 = 采样个数 * 采样格式大小 * 声道数
    fsize = c->frame_size * av_get_bytes_per_sample(stream->codecpar->format) *
            stream->codecpar->channels;
    printf("frame size: %d\n", fsize);

    fifo = av_fifo_alloc(fsize * 5);
    if (!fifo)
    {
        printf("av_fifo_alloc failed\n");
        goto end;
    }

    // 创建线程
    pthread_t tid;
    pthread_mutex_init(&lock, NULL);
    pthread_create(&tid, NULL, thread_encode, NULL);

    // 读取帧并进行重采样，编码，发送
    AVPacket read_pkt;
    while ((av_read_frame(in_context, &read_pkt) >= 0) && (!thread_encode_exit))
    {
        if (read_pkt.stream_index == streamid)
        {
            pthread_mutex_lock(&lock);
            av_fifo_generic_write(fifo, read_pkt.buf->data, read_pkt.size, NULL);
            pthread_mutex_unlock(&lock);
        }
        av_packet_unref(&read_pkt);
    }
    thread_encode_exit = 1;

end:
    pthread_join(tid, NULL);
    pthread_mutex_destroy(&lock);
    if (c)
        avcodec_free_context(&c);
    if (output_frame)
        av_frame_free(&output_frame);
    if (recv_ptk)
        av_packet_free(&recv_ptk);
    if (swr_ctx)
        swr_free(&swr_ctx);
    if (out_context)
        avformat_free_context(out_context);
    if (in_context)
        avformat_close_input(&in_context);
    if (fifo)
        av_fifo_free(fifo);

    return 0;
}

void *thread_encode(void *)
{
    int ret;
    int64_t pts = 0;

    uint8_t *buf = av_malloc(fsize);
    if (!buf)
    {
        printf("av_malloc failed\n");
        goto end;
    }
    AVPacket *recv_ptk = av_packet_alloc();
    if (!recv_ptk)
    {
        printf("av_packet_alloc failed\n");
        goto end;
    }

    while (!thread_encode_exit)
    {
        pthread_mutex_lock(&lock);
        if (av_fifo_size(fifo) < fsize)
        {
            // 不够一帧aac编码所需的数据
            pthread_mutex_unlock(&lock);
            usleep(2 * 1000);
            continue;
        }
        av_fifo_generic_read(fifo, buf, fsize, NULL);
        pthread_mutex_unlock(&lock);

        // 重采样
        ret = swr_convert(swr_ctx, output_frame->data, output_frame->nb_samples,
                          (const uint8_t **)&buf, output_frame->nb_samples);
        if (ret < 0)
        {
            printf("swr_convert failed\n");
            goto end;
        }

        output_frame->pts = pts;
        pts += output_frame->nb_samples;

        // 发送帧给编码器
        ret = avcodec_send_frame(c, output_frame);
        if (ret < 0)
        {
            printf("avcodec_send_frame failed\n");
            goto end;
        }

        // 接收编码后的数据包
        while (ret >= 0)
        {
            ret = avcodec_receive_packet(c, recv_ptk);
            if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            {
                break;
            }
            else if (ret < 0)
            {
                printf("avcodec_receive_packet error (errmsg '%s')\n", av_err2str(ret));
                goto end;
            }

            recv_ptk->stream_index = out_stream->index;
            av_packet_rescale_ts(recv_ptk, c->time_base, out_stream->time_base);

            ret = av_interleaved_write_frame(out_context, recv_ptk);
            if (ret < 0)
            {
                printf("av_interleaved_write_frame failed\n");
                av_packet_unref(recv_ptk);
                goto end;
            }
            av_packet_unref(recv_ptk);
        }
    }

end:
    if (buf)
        av_free(buf);
    if (recv_ptk)
        av_packet_free(&recv_ptk);

    thread_encode_exit = 1;
    return NULL;
}