Convert an input audio file to AAC in an MP4 container using FFmpeg.Formats other than MP4 are supported based on the output file extension.
/*
* Copyright (c) 2013-2018 Andreas Unterweger
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
/**
* @file
* Simple audio converter
*
* @example transcode_aac.c
* Convert an input audio file to AAC in an MP4 container using FFmpeg.
* Formats other than MP4 are supported based on the output file extension.
* @author Andreas Unterweger (dustsigns@gmail.com)
*/
#include <stdio.h>
/* The output bit rate in bit/s */
#define OUTPUT_BIT_RATE 96000
/* The number of output channels */
#define OUTPUT_CHANNELS 2
/**
* Open an input file and the required decoder.
* @param filename File to be opened
* @param[out] input_format_context Format context of opened file
* @param[out] input_codec_context Codec context of opened file
* @return Error code (0 if successful)
*/
{
/* Open the input file to read from it. */
fprintf(stderr, "Could not open input file '%s' (error '%s')\n",
*input_format_context =
NULL;
}
/* Get information on the input file (number of streams etc.). */
fprintf(stderr, "Could not open find stream info (error '%s')\n",
}
/* Make sure that there is only one stream in the input file. */
if ((*input_format_context)->nb_streams != 1) {
fprintf(stderr, "Expected one audio input stream, but found %d\n",
(*input_format_context)->nb_streams);
}
/* Find a decoder for the audio stream. */
if (!(input_codec =
avcodec_find_decoder((*input_format_context)->streams[0]->codecpar->codec_id))) {
fprintf(stderr, "Could not find input codec\n");
}
/* Allocate a new decoding context. */
if (!avctx) {
fprintf(stderr, "Could not allocate a decoding context\n");
}
/* Initialize the stream parameters with demuxer information. */
}
/* Open the decoder for the audio stream to use it later. */
fprintf(stderr, "Could not open input codec (error '%s')\n",
}
/* Save the decoder context for easier access later. */
*input_codec_context = avctx;
return 0;
}
/**
* Open an output file and the required encoder.
* Also set some basic encoder parameters.
* Some of these parameters are based on the input file's parameters.
* @param filename File to be opened
* @param input_codec_context Codec context of input file
* @param[out] output_format_context Format context of output file
* @param[out] output_codec_context Codec context of output file
* @return Error code (0 if successful)
*/
{
/* Open the output file to write to it. */
fprintf(stderr, "Could not open output file '%s' (error '%s')\n",
}
/* Create a new format context for the output container format. */
fprintf(stderr, "Could not allocate output format context\n");
}
/* Associate the output file (pointer) with the container format context. */
(*output_format_context)->pb = output_io_context;
/* Guess the desired container format based on the file extension. */
fprintf(stderr, "Could not find output file format\n");
}
if (!((*output_format_context)->url =
av_strdup(filename))) {
fprintf(stderr, "Could not allocate url.\n");
}
/* Find the encoder to be used by its name. */
fprintf(stderr, "Could not find an AAC encoder.\n");
}
/* Create a new audio stream in the output file container. */
fprintf(stderr, "Could not create new stream\n");
}
if (!avctx) {
fprintf(stderr, "Could not allocate an encoding context\n");
}
/* Set the basic encoder parameters.
* The input file's sample rate is used to avoid a sample rate conversion. */
/* Allow the use of the experimental AAC encoder. */
/* Set the sample rate for the container. */
/* Some container formats (like MP4) require global headers to be present.
* Mark the encoder so that it behaves accordingly. */
/* Open the encoder for the audio stream to use it later. */
fprintf(stderr, "Could not open output codec (error '%s')\n",
}
fprintf(stderr, "Could not initialize stream parameters\n");
}
/* Save the encoder context for easier access later. */
*output_codec_context = avctx;
return 0;
*output_format_context =
NULL;
}
/**
* Initialize one data packet for reading or writing.
* @param[out] packet Packet to be initialized
* @return Error code (0 if successful)
*/
{
fprintf(stderr, "Could not allocate packet\n");
}
return 0;
}
/**
* Initialize one audio frame for reading from the input file.
* @param[out] frame Frame to be initialized
* @return Error code (0 if successful)
*/
{
fprintf(stderr, "Could not allocate input frame\n");
}
return 0;
}
/**
* Initialize the audio resampler based on the input and output codec settings.
* If the input and output sample formats differ, a conversion is required
* libswresample takes care of this, but requires initialization.
* @param input_codec_context Codec context of the input file
* @param output_codec_context Codec context of the output file
* @param[out] resample_context Resample context for the required conversion
* @return Error code (0 if successful)
*/
{
/*
* Create a resampler context for the conversion.
* Set the conversion parameters.
* Default channel layouts based on the number of channels
* are assumed for simplicity (they are sometimes not detected
* properly by the demuxer and/or decoder).
*/
if (!*resample_context) {
fprintf(stderr, "Could not allocate resample context\n");
}
/*
* Perform a sanity check so that the number of converted samples is
* not greater than the number of samples to be converted.
* If the sample rates differ, this case has to be handled differently
*/
/* Open the resampler with the specified parameters. */
fprintf(stderr, "Could not open resample context\n");
}
return 0;
}
/**
* Initialize a FIFO buffer for the audio samples to be encoded.
* @param[out] fifo Sample buffer
* @param output_codec_context Codec context of the output file
* @return Error code (0 if successful)
*/
{
/* Create the FIFO buffer based on the specified output sample format. */
fprintf(stderr, "Could not allocate FIFO\n");
}
return 0;
}
/**
* Write the header of the output file container.
* @param output_format_context Format context of the output file
* @return Error code (0 if successful)
*/
{
fprintf(stderr, "Could not write output file header (error '%s')\n",
}
return 0;
}
/**
* Decode one audio frame from the input file.
* @param frame Audio frame to be decoded
* @param input_format_context Format context of the input file
* @param input_codec_context Codec context of the input file
* @param[out] data_present Indicates whether data has been decoded
* @param[out] finished Indicates whether the end of file has
* been reached and all data has been
* decoded. If this flag is false, there
* is more data to be decoded, i.e., this
* function has to be called again.
* @return Error code (0 if successful)
*/
int *data_present, int *finished)
{
/* Packet used for temporary storage. */
/* Read one audio frame from the input file into a temporary packet. */
/* If we are at the end of the file, flush the decoder below. */
*finished = 1;
else {
fprintf(stderr, "Could not read frame (error '%s')\n",
}
}
/* Send the audio frame stored in the temporary packet to the decoder.
* The input audio stream decoder is used to do this. */
fprintf(stderr, "Could not send packet for decoding (error '%s')\n",
}
/* Receive one frame from the decoder. */
/* If the decoder asks for more data to be able to decode a frame,
* return indicating that no data is present. */
/* If the end of the input file is reached, stop decoding. */
*finished = 1;
fprintf(stderr, "Could not decode frame (error '%s')\n",
/* Default case: Return decoded data. */
} else {
*data_present = 1;
}
}
/**
* Initialize a temporary storage for the specified number of audio samples.
* The conversion requires temporary storage due to the different format.
* The number of audio samples to be allocated is specified in frame_size.
* @param[out] converted_input_samples Array of converted samples. The
* dimensions are reference, channel
* (for multi-channel audio), sample.
* @param output_codec_context Codec context of the output file
* @param frame_size Number of samples to be converted in
* each round
* @return Error code (0 if successful)
*/
{
/* Allocate as many pointers as there are audio channels.
* Each pointer will later point to the audio samples of the corresponding
* channels (although it may be NULL for interleaved formats).
*/
if (!(*converted_input_samples = calloc(output_codec_context->
channels,
sizeof(**converted_input_samples)))) {
fprintf(stderr, "Could not allocate converted input sample pointers\n");
}
/* Allocate memory for the samples of all channels in one consecutive
* block for convenience. */
fprintf(stderr,
"Could not allocate converted input samples (error '%s')\n",
av_freep(&(*converted_input_samples)[0]);
free(*converted_input_samples);
}
return 0;
}
/**
* Convert the input audio samples into the output sample format.
* The conversion happens on a per-frame basis, the size of which is
* specified by frame_size.
* @param input_data Samples to be decoded. The dimensions are
* channel (for multi-channel audio), sample.
* @param[out] converted_data Converted samples. The dimensions are channel
* (for multi-channel audio), sample.
* @param frame_size Number of samples to be converted
* @param resample_context Resample context for the conversion
* @return Error code (0 if successful)
*/
{
/* Convert the samples using the resampler. */
fprintf(stderr, "Could not convert input samples (error '%s')\n",
}
return 0;
}
/**
* Add converted input audio samples to the FIFO buffer for later processing.
* @param fifo Buffer to add the samples to
* @param converted_input_samples Samples to be added. The dimensions are channel
* (for multi-channel audio), sample.
* @param frame_size Number of samples to be converted
* @return Error code (0 if successful)
*/
{
/* Make the FIFO as large as it needs to be to hold both,
* the old and the new samples. */
fprintf(stderr, "Could not reallocate FIFO\n");
}
/* Store the new samples in the FIFO buffer. */
fprintf(stderr, "Could not write data to FIFO\n");
}
return 0;
}
/**
* Read one audio frame from the input file, decode, convert and store
* it in the FIFO buffer.
* @param fifo Buffer used for temporary storage
* @param input_format_context Format context of the input file
* @param input_codec_context Codec context of the input file
* @param output_codec_context Codec context of the output file
* @param resampler_context Resample context for the conversion
* @param[out] finished Indicates whether the end of file has
* been reached and all data has been
* decoded. If this flag is false,
* there is more data to be decoded,
* i.e., this function has to be called
* again.
* @return Error code (0 if successful)
*/
int *finished)
{
/* Temporary storage of the input samples of the frame read from the file. */
/* Temporary storage for the converted input samples. */
int data_present = 0;
/* Initialize temporary storage for one input frame. */
/* Decode one frame worth of audio samples. */
input_codec_context, &data_present, finished))
/* If we are at the end of the file and there are no more samples
* in the decoder which are delayed, we are actually finished.
* This must not be treated as an error. */
if (*finished) {
}
/* If there is decoded data, convert and store it. */
if (data_present) {
/* Initialize the temporary storage for the converted input samples. */
/* Convert the input samples to the desired output sample format.
* This requires a temporary storage provided by converted_input_samples. */
/* Add the converted input samples to the FIFO buffer for later processing. */
}
if (converted_input_samples) {
free(converted_input_samples);
}
}
/**
* Initialize one input frame for writing to the output file.
* The frame will be exactly frame_size samples large.
* @param[out] frame Frame to be initialized
* @param output_codec_context Codec context of the output file
* @param frame_size Size of the frame
* @return Error code (0 if successful)
*/
{
/* Create a new frame to store the audio samples. */
fprintf(stderr, "Could not allocate output frame\n");
}
/* Set the frame's parameters, especially its size and format.
* av_frame_get_buffer needs this to allocate memory for the
* audio samples of the frame.
* Default channel layouts based on the number of channels
* are assumed for simplicity. */
(*frame)->format = output_codec_context->
sample_fmt;
(*frame)->sample_rate = output_codec_context->
sample_rate;
/* Allocate the samples of the created frame. This call will make
* sure that the audio frame can hold as many samples as specified. */
fprintf(stderr, "Could not allocate output frame samples (error '%s')\n",
}
return 0;
}
/* Global timestamp for the audio frames. */
/**
* Encode one frame worth of audio to the output file.
* @param frame Samples to be encoded
* @param output_format_context Format context of the output file
* @param output_codec_context Codec context of the output file
* @param[out] data_present Indicates whether data has been
* encoded
* @return Error code (0 if successful)
*/
int *data_present)
{
/* Packet used for temporary storage. */
/* Set a timestamp based on the sample rate for the container. */
}
/* Send the audio frame stored in the temporary packet to the encoder.
* The output audio stream encoder is used to do this. */
/* The encoder signals that it has nothing more to encode. */
fprintf(stderr, "Could not send packet for encoding (error '%s')\n",
}
/* Receive one encoded frame from the encoder. */
/* If the encoder asks for more data to be able to provide an
* encoded frame, return indicating that no data is present. */
/* If the last frame has been encoded, stop encoding. */
fprintf(stderr, "Could not encode frame (error '%s')\n",
/* Default case: Return encoded data. */
} else {
*data_present = 1;
}
/* Write one audio frame from the temporary packet to the output file. */
if (*data_present &&
fprintf(stderr, "Could not write frame (error '%s')\n",
}
}
/**
* Load one audio frame from the FIFO buffer, encode and write it to the
* output file.
* @param fifo Buffer used for temporary storage
* @param output_format_context Format context of the output file
* @param output_codec_context Codec context of the output file
* @return Error code (0 if successful)
*/
{
/* Temporary storage of the output samples of the frame written to the file. */
/* Use the maximum number of possible samples per frame.
* If there is less than the maximum possible frame size in the FIFO
* buffer use this number. Otherwise, use the maximum possible frame size. */
int data_written;
/* Initialize temporary storage for one output frame. */
/* Read as many samples from the FIFO buffer as required to fill the frame.
* The samples are stored in the frame temporarily. */
fprintf(stderr, "Could not read data from FIFO\n");
}
/* Encode one frame worth of audio samples. */
output_codec_context, &data_written)) {
}
return 0;
}
/**
* Write the trailer of the output file container.
* @param output_format_context Format context of the output file
* @return Error code (0 if successful)
*/
{
fprintf(stderr, "Could not write output file trailer (error '%s')\n",
}
return 0;
}
int main(
int argc,
char **argv)
{
if (argc != 3) {
fprintf(stderr, "Usage: %s <input file> <output file>\n", argv[0]);
exit(1);
}
/* Open the input file for reading. */
&input_codec_context))
/* Open the output file for writing. */
&output_format_context, &output_codec_context))
/* Initialize the resampler to be able to convert audio sample formats. */
&resample_context))
/* Initialize the FIFO buffer to store audio samples to be encoded. */
/* Write the header of the output file container. */
/* Loop as long as we have input samples to read or output samples
* to write; abort as soon as we have neither. */
while (1) {
/* Use the encoder's desired frame size for processing. */
const int output_frame_size = output_codec_context->frame_size;
int finished = 0;
/* Make sure that there is one frame worth of samples in the FIFO
* buffer so that the encoder can do its work.
* Since the decoder's and the encoder's frame size may differ, we
* need to FIFO buffer to store as many frames worth of input samples
* that they make up at least one frame worth of output samples. */
/* Decode one frame worth of audio samples, convert it to the
* output sample format and put it into the FIFO buffer. */
input_codec_context,
output_codec_context,
resample_context, &finished))
/* If we are at the end of the input file, we continue
* encoding the remaining audio samples to the output file. */
if (finished)
break;
}
/* If we have enough samples for the encoder, we encode them.
* At the end of the file, we pass the remaining samples to
* the encoder. */
/* Take one frame worth of audio samples from the FIFO buffer,
* encode it and write it to the output file. */
output_codec_context))
/* If we are at the end of the input file and have encoded
* all remaining samples, we can exit this loop and finish. */
if (finished) {
int data_written;
/* Flush the encoder as it may have delayed frames. */
do {
data_written = 0;
output_codec_context, &data_written))
} while (data_written);
break;
}
}
/* Write the trailer of the output file container. */
if (fifo)
if (output_codec_context)
if (output_format_context) {
}
if (input_codec_context)
if (input_format_context)
}