I'm am currently using C# invokes to call the FFmpeg APIs to handle video and audio. I have the following code in place to extract the audio from a video and write it to a file.
while (ffmpeg.av_read_frame(formatContext, &packet) >= 0)
{
if (packet.stream_index == streamIndex)
{
while (packet.size > 0)
{
int frameDecoded;
int frameDecodedResult = ffmpeg.avcodec_decode_audio4(codecContext, frame, &frameDecoded, packet);
if (frameDecoded > 0 && frameDecodedResult >= 0)
{
//writeAudio.WriteFrame(frame);
packet.data += totalBytesDecoded;
packet.size -= totalBytesDecoded;
}
}
frameIndex++;
}
Avcodec.av_free_packet(&packet);
}
This is all working correctly. I'm currently using the FFmpeg.AutoGen project for the API access.
I want to be able to increase/decrease the volume of the audio before its written to the file, but I cannot seem to find a command or any help with this. Does it have to be done manually?
Update 1:
After receiving some help, this is the class layout I have:
public unsafe class FilterVolume
{
#region Private Member Variables
private AVFilterGraph* m_filterGraph = null;
private AVFilterContext* m_aBufferSourceFilterContext = null;
private AVFilterContext* m_aBufferSinkFilterContext = null;
#endregion
#region Private Constant Member Variables
private const int EAGAIN = 11;
#endregion
public FilterVolume(AVCodecContext* codecContext, AVStream* stream, float volume)
{
CodecContext = codecContext;
Stream = stream;
Volume = volume;
Initialise();
}
public AVFrame* Adjust(AVFrame* frame)
{
AVFrame* returnFilteredFrame = ffmpeg.av_frame_alloc();
if (m_aBufferSourceFilterContext != null && m_aBufferSinkFilterContext != null)
{
int bufferSourceAddFrameResult = ffmpeg.av_buffersrc_add_frame(m_aBufferSourceFilterContext, frame);
if (bufferSourceAddFrameResult < 0)
{
}
int bufferSinkGetFrameResult = ffmpeg.av_buffersink_get_frame(m_aBufferSinkFilterContext, returnFilteredFrame);
if (bufferSinkGetFrameResult < 0 && bufferSinkGetFrameResult != -EAGAIN)
{
}
}
return returnFilteredFrame;
}
public void Dispose()
{
Cleanup(m_filterGraph);
}
#region Private Properties
private AVCodecContext* CodecContext { get; set; }
private AVStream* Stream { get; set; }
private float Volume { get; set; }
#endregion
#region Private Setup Helper Functions
private void Initialise()
{
m_filterGraph = GetAllocatedFilterGraph();
string aBufferFilterArguments = string.Format("sample_fmt={0}:channel_layout={1}:sample_rate={2}:time_base={3}/{4}",
(int)CodecContext->sample_fmt,
CodecContext->channel_layout,
CodecContext->sample_rate,
Stream->time_base.num,
Stream->time_base.den);
AVFilterContext* aBufferSourceFilterContext = CreateFilter("abuffer", m_filterGraph, aBufferFilterArguments);
AVFilterContext* volumeFilterContext = CreateFilter("volume", m_filterGraph, string.Format("volume={0}", Volume));
AVFilterContext* aBufferSinkFilterContext = CreateFilter("abuffersink", m_filterGraph);
LinkFilter(aBufferSourceFilterContext, volumeFilterContext);
LinkFilter(volumeFilterContext, aBufferSinkFilterContext);
SetFilterGraphConfiguration(m_filterGraph, null);
m_aBufferSourceFilterContext = aBufferSourceFilterContext;
m_aBufferSinkFilterContext = aBufferSinkFilterContext;
}
#endregion
#region Private Cleanup Helper Functions
private static void Cleanup(AVFilterGraph* filterGraph)
{
if (filterGraph != null)
{
ffmpeg.avfilter_graph_free(&filterGraph);
}
}
#endregion
#region Provate Helpers
private AVFilterGraph* GetAllocatedFilterGraph()
{
AVFilterGraph* filterGraph = ffmpeg.avfilter_graph_alloc();
if (filterGraph == null)
{
}
return filterGraph;
}
private AVFilter* GetFilterByName(string name)
{
AVFilter* filter = ffmpeg.avfilter_get_by_name(name);
if (filter == null)
{
}
return filter;
}
private void SetFilterGraphConfiguration(AVFilterGraph* filterGraph, void* logContext)
{
int filterGraphConfigResult = ffmpeg.avfilter_graph_config(filterGraph, logContext);
if (filterGraphConfigResult < 0)
{
}
}
private AVFilterContext* CreateFilter(string filterName, AVFilterGraph* filterGraph, string filterArguments = null)
{
AVFilter* filter = GetFilterByName(filterName);
AVFilterContext* filterContext;
int aBufferFilterCreateResult = ffmpeg.avfilter_graph_create_filter(&filterContext, filter, filterName, filterArguments, null, filterGraph);
if (aBufferFilterCreateResult < 0)
{
}
return filterContext;
}
private void LinkFilter(AVFilterContext* source, AVFilterContext* destination)
{
int filterLinkResult = ffmpeg.avfilter_link(source, 0, destination, 0);
if (filterLinkResult < 0)
{
}
}
#endregion
}
The Adjust() function is called after a frame is decoded. I'm currently getting a -22 error when av_buffersrc_add_frame() is called. This indicates that a parameter is invalid, but after debugging, I cannot see anything that would be causing this.
This is how the code is called:
while (ffmpeg.av_read_frame(formatContext, &packet) >= 0)
{
if (packet.stream_index == streamIndex)
{
while (packet.size > 0)
{
int frameDecoded;
int frameDecodedResult = ffmpeg.avcodec_decode_audio4(codecContext, frame, &frameDecoded, packet);
if (frameDecoded > 0 && frameDecodedResult >= 0)
{
AVFrame* filteredFrame = m_filterVolume.Adjust(frame);
//writeAudio.WriteFrame(filteredFrame);
packet.data += totalBytesDecoded;
packet.size -= totalBytesDecoded;
}
}
frameIndex++;
}
Avcodec.av_free_packet(&packet);
}
Update 2:
Cracked it. The "channel_layout" option in the filter argument string is supposed to be a hexadecimal. This is what the string formatting should look like:
string aBufferFilterArguments = string.Format("sample_fmt={0}:channel_layout=0x{1}:sample_rate={2}:time_base={3}/{4}",
(int)CodecContext->sample_fmt,
CodecContext->channel_layout,
CodecContext->sample_rate,
Stream->time_base.num,
Stream->time_base.den);
I do not know what API you are using, but ffmpeg has a command that allows to increase or decrease audio:
Decrease to half:
Increase 50%:
or in dB:
Hopes it helps you
What you need to do is build a filter graph and process the audio stream through that graph. In your case, the graph is just INPUT ("abuffer") -> VOLUME -> OUTPUT ("abuffersink"). Here is a sample console app that demonstrates that. It's loosely based on ffmpeg samples filtering_audio, filter_audio and remuxing.
You can use it like this:
And here is the code:
It uses a utility InteropHelper class derived from AutoGen's: