Skip to content

feature/pcmu-to-aac #265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cedricve wants to merge 4 commits into
base: master
Choose a base branch
from
Open

feature/pcmu-to-aac #265

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a7e6895
Implement PCM_MULAW to AAC transcoding functionality
cedricve Mar 19, 2026
945ceea
Add LPCM audio support and enhance PCM_MULAW to AAC transcoding
cedricve Mar 19, 2026
204ae3f
Refactor PCM to AAC transcoder for improved concurrency and error han…
cedricve Mar 19, 2026
642a89a
Enhance audio/video synchronization and improve flushing timeout in A…
cedricve Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
86 changes: 86 additions & 0 deletions machinery/src/capture/gortsplib.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -339,6 +339,40 @@ func (g *Golibrtsp) Connect(ctx context.Context, ctxOtel context.Context) (err e
}
}

// Look for audio stream.
// find the LPCM media and format
audioFormaLPCM, audioMediLPCM := FindLPCM(desc, false)
g.AudioLPCMMedia = audioMediLPCM
g.AudioLPCMForma = audioFormaLPCM
if audioMediLPCM == nil {
log.Log.Debug("capture.golibrtsp.Connect(LPCM): " + "audio media not found")
} else {
_, err = g.Client.Setup(desc.BaseURL, audioMediLPCM, 0, 0)
if err != nil {
log.Log.Error("capture.golibrtsp.Connect(LPCM): " + err.Error())
} else {
audiortpDec, err := audioFormaLPCM.CreateDecoder()
if err != nil {
log.Log.Error("capture.golibrtsp.Connect(LPCM): " + err.Error())
} else {
g.AudioLPCMDecoder = audiortpDec
streamIndex := len(g.Streams)
g.Streams = append(g.Streams, packets.Stream{
Index: streamIndex,
Name: "LPCM",
IsVideo: false,
IsAudio: true,
IsBackChannel: false,
SampleRate: audioFormaLPCM.SampleRate,
Channels: audioFormaLPCM.ChannelCount,
BitDepth: audioFormaLPCM.BitDepth,
})

g.AudioLPCMIndex = int8(len(g.Streams)) - 1
}
}
}

// Look for audio stream.
// find the G711 media and format
audioForma, audioMedi := FindPCMU(desc, false)
Expand Down Expand Up @@ -367,6 +401,8 @@ func (g *Golibrtsp) Connect(ctx context.Context, ctxOtel context.Context) (err e
IsVideo: false,
IsAudio: true,
IsBackChannel: false,
SampleRate: defaultPCMUSampleRate,
Channels: defaultPCMUChannels,
})

// Set the index for the audio
Expand Down Expand Up @@ -509,6 +545,8 @@ func (g *Golibrtsp) ConnectBackChannel(ctx context.Context, ctxRunAgent context.
IsVideo: false,
IsAudio: true,
IsBackChannel: true,
SampleRate: defaultPCMUSampleRate,
Channels: defaultPCMUChannels,
})
// Set the index for the audio
g.AudioG711IndexBackChannel = int8(len(g.Streams)) - 1
Expand All @@ -521,6 +559,39 @@ func (g *Golibrtsp) ConnectBackChannel(ctx context.Context, ctxRunAgent context.
func (g *Golibrtsp) Start(ctx context.Context, streamType string, queue *packets.Queue, configuration *models.Configuration, communication *models.Communication) (err error) {
log.Log.Debug("capture.golibrtsp.Start(): started")

// called when a MULAW audio RTP packet arrives
if g.AudioLPCMMedia != nil && g.AudioLPCMForma != nil {
g.Client.OnPacketRTP(g.AudioLPCMMedia, g.AudioLPCMForma, func(rtppkt *rtp.Packet) {
pts, ok := g.Client.PacketPTS(g.AudioLPCMMedia, rtppkt)
pts2, ok := g.Client.PacketPTS2(g.AudioLPCMMedia, rtppkt)
if !ok {
log.Log.Debug("capture.golibrtsp.Start(): " + "unable to get PTS")
return
}
Comment on lines +565 to +570

op, err := g.AudioLPCMDecoder.Decode(rtppkt)
if err != nil {
log.Log.Error("capture.golibrtsp.Start(): " + err.Error())
return
}

pkt := packets.Packet{
IsKeyFrame: false,
Packet: rtppkt,
Data: op,
Time: pts2,
TimeLegacy: pts,
CompositionTime: pts2,
CurrentTime: time.Now().UnixMilli(),
Idx: g.AudioLPCMIndex,
IsVideo: false,
IsAudio: true,
Codec: "LPCM",
}
queue.WritePacket(pkt)
})
}

// called when a MULAW audio RTP packet arrives
if g.AudioG711Media != nil && g.AudioG711Forma != nil {
g.Client.OnPacketRTP(g.AudioG711Media, g.AudioG711Forma, func(rtppkt *rtp.Packet) {
Expand Down Expand Up @@ -1259,6 +1330,21 @@ func FindPCMU(desc *description.Session, isBackChannel bool) (*format.G711, *des
return nil, nil
}

func FindLPCM(desc *description.Session, isBackChannel bool) (*format.LPCM, *description.Media) {
for _, media := range desc.Medias {
if media.IsBackChannel == isBackChannel {
for _, forma := range media.Formats {
if lpcm, ok := forma.(*format.LPCM); ok {
if lpcm.SampleRate > 0 && lpcm.ChannelCount > 0 && lpcm.BitDepth > 0 {
return lpcm, media
}
}
}
}
}
return nil, nil
}

func FindOPUS(desc *description.Session, isBackChannel bool) (*format.Opus, *description.Media) {
for _, media := range desc.Medias {
if media.IsBackChannel == isBackChannel {
Expand Down
Loading
Loading