rtmp: support publishing G711 and LPCM tracks (#2857) (#2884)

README.md

@@ -22,11 +22,11 @@ Live streams can be published to the server with:
 |--------|--------|------------|------------|
 |[SRT clients](#srt-clients)||H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3|
 |[SRT cameras and servers](#srt-cameras-and-servers)||H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3|
-|[WebRTC clients](#webrtc-clients)|Browser-based, WHIP|AV1, VP9, VP8, H264|Opus, G722, G711|
-|[WebRTC servers](#webrtc-servers)|WHEP|AV1, VP9, VP8, H264|Opus, G722, G711|
-|[RTSP clients](#rtsp-clients)|UDP, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711, LPCM and any RTP-compatible codec|
-|[RTSP cameras and servers](#rtsp-cameras-and-servers)|UDP, UDP-Multicast, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711, LPCM and any RTP-compatible codec|
-|[RTMP clients](#rtmp-clients)|RTMP, RTMPS, Enhanced RTMP|AV1, VP9, H265, H264|MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3)|
+|[WebRTC clients](#webrtc-clients)|Browser-based, WHIP|AV1, VP9, VP8, H264|Opus, G722, G711 (PCMA, PCMU)|
+|[WebRTC servers](#webrtc-servers)|WHEP|AV1, VP9, VP8, H264|Opus, G722, G711 (PCMA, PCMU)|
+|[RTSP clients](#rtsp-clients)|UDP, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711 (PCMA, PCMU), LPCM and any RTP-compatible codec|
+|[RTSP cameras and servers](#rtsp-cameras-and-servers)|UDP, UDP-Multicast, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711 (PCMA, PCMU), LPCM and any RTP-compatible codec|
+|[RTMP clients](#rtmp-clients)|RTMP, RTMPS, Enhanced RTMP|AV1, VP9, H265, H264|MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), G711 (PCMA, PCMU), LPCM|
 |[RTMP cameras and servers](#rtmp-cameras-and-servers)|RTMP, RTMPS, Enhanced RTMP|H264|MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3)|
 |[HLS cameras and servers](#hls-cameras-and-servers)|Low-Latency HLS, MP4-based HLS, legacy HLS|AV1, VP9, H265, H264|Opus, MPEG-4 Audio (AAC)|
 |[UDP/MPEG-TS](#udpmpeg-ts)|Unicast, broadcast, multicast|H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3|
@@ -37,16 +37,16 @@ And can be read from the server with:
 |protocol|variants|video codecs|audio codecs|
 |--------|--------|------------|------------|
 |[SRT](#srt)||H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3|
-|[WebRTC](#webrtc)|Browser-based, WHEP|AV1, VP9, VP8, H264|Opus, G722, G711|
-|[RTSP](#rtsp)|UDP, UDP-Multicast, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711, LPCM and any RTP-compatible codec|
+|[WebRTC](#webrtc)|Browser-based, WHEP|AV1, VP9, VP8, H264|Opus, G722, G711 (PCMA, PCMU)|
+|[RTSP](#rtsp)|UDP, UDP-Multicast, TCP, RTSPS|AV1, VP9, VP8, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG and any RTP-compatible codec|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G726, G722, G711 (PCMA, PCMU), LPCM and any RTP-compatible codec|
 |[RTMP](#rtmp)|RTMP, RTMPS, Enhanced RTMP|H264|MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3)|
 |[HLS](#hls)|Low-Latency HLS, MP4-based HLS, legacy HLS|AV1, VP9, H265, H264|Opus, MPEG-4 Audio (AAC)|
 
 And can be recorded with:
 
 |format|video codecs|audio codecs|
 |------|------------|------------|
-|[fMP4](#record-streams-to-disk)|AV1, VP9, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G711, LPCM|
+|[fMP4](#record-streams-to-disk)|AV1, VP9, H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video, M-JPEG|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3, G711 (PCMA, PCMU), LPCM|
 |[MPEG-TS](#record-streams-to-disk)|H265, H264, MPEG-4 Video (H263, Xvid), MPEG-1/2 Video|Opus, MPEG-4 Audio (AAC), MPEG-1/2 Audio (MP3), AC-3|
 
 **Features**

go.mod

@@ -8,7 +8,7 @@ require (
 	github.com/alecthomas/kong v0.8.1
 	github.com/aler9/writerseeker v1.1.0
 	github.com/bluenviron/gohlslib v1.2.0
-	github.com/bluenviron/gortsplib/v4 v4.6.2
+	github.com/bluenviron/gortsplib/v4 v4.6.3-0.20240107120136-f9eb8e573bbe
 	github.com/bluenviron/mediacommon v1.6.1-0.20231228213201-7bb211dba7e1
 	github.com/datarhei/gosrt v0.5.5
 	github.com/fsnotify/fsnotify v1.7.0

go.sum

@@ -22,8 +22,8 @@ github.com/benburkert/openpgp v0.0.0-20160410205803-c2471f86866c h1:8XZeJrs4+ZYh
 github.com/benburkert/openpgp v0.0.0-20160410205803-c2471f86866c/go.mod h1:x1vxHcL/9AVzuk5HOloOEPrtJY0MaalYr78afXZ+pWI=
 github.com/bluenviron/gohlslib v1.2.0 h1:Hrx2/n/AcmKKIV+MjZLKs5kmW+O7xCdUSPJQoS39JKw=
 github.com/bluenviron/gohlslib v1.2.0/go.mod h1:kG/Sjebsxnf5asMGaGcQ0aSvtFGNChJPgctds2wDHOI=
-github.com/bluenviron/gortsplib/v4 v4.6.2 h1:CGIsxpnUFvSlIxnSFS0oFSSfwsHMmBCmYcrGAtIcwXc=
-github.com/bluenviron/gortsplib/v4 v4.6.2/go.mod h1:dN1YjyPNMfy/NwC17Ga6MiIMiUoQfg5GL7LGsVHa0Jo=
+github.com/bluenviron/gortsplib/v4 v4.6.3-0.20240107120136-f9eb8e573bbe h1:eVx4BU4mF26UK/SQlsnIkeCIraQR8AcJf42ymYR3pQE=
+github.com/bluenviron/gortsplib/v4 v4.6.3-0.20240107120136-f9eb8e573bbe/go.mod h1:UqdkRR5YvKHP/wHEQQySJFKJm6tIZcftdP7cNszIZ1g=
 github.com/bluenviron/mediacommon v1.6.1-0.20231228213201-7bb211dba7e1 h1:f8XDAHvgPbT+n5qf73REdUo9kLmGpP4HNgphKI/8fGE=
 github.com/bluenviron/mediacommon v1.6.1-0.20231228213201-7bb211dba7e1/go.mod h1:Ij/kE1LEucSjryNBVTyPL/gBI0d6/Css3f5PyrM957w=
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=

internal/formatprocessor/ac3.go

@@ -53,14 +53,13 @@ func (t *formatProcessorAC3) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/av1.go

@@ -55,14 +55,13 @@ func (t *formatProcessorAV1) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/g711.go

@@ -41,6 +41,7 @@ func newG711(
 func (t *formatProcessorG711) createEncoder() error {
 	t.encoder = &rtpsimpleaudio.Encoder{
 		PayloadMaxSize: t.udpMaxPayloadSize - 12,
+		PayloadType:    t.format.PayloadType(),
 	}
 	return t.encoder.Init()
 }
@@ -52,11 +53,10 @@ func (t *formatProcessorG711) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = []*rtp.Packet{pkt}
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	pkt.Timestamp += ts
-
-	u.RTPPackets = []*rtp.Packet{pkt}
+	u.RTPPackets[0].Timestamp += ts
 
 	return nil
 }

internal/formatprocessor/g711_test.go

@@ -0,0 +1,62 @@
+package formatprocessor
+
+import (
+	"testing"
+
+	"github.com/bluenviron/gortsplib/v4/pkg/format"
+	"github.com/bluenviron/mediamtx/internal/unit"
+	"github.com/pion/rtp"
+	"github.com/stretchr/testify/require"
+)
+
+func TestG611Encode(t *testing.T) {
+	t.Run("alaw", func(t *testing.T) {
+		forma := &format.G711{
+			MULaw: false,
+		}
+
+		p, err := New(1472, forma, true)
+		require.NoError(t, err)
+
+		unit := &unit.G711{
+			Samples: []byte{1, 2, 3, 4},
+		}
+
+		err = p.ProcessUnit(unit)
+		require.NoError(t, err)
+		require.Equal(t, []*rtp.Packet{{
+			Header: rtp.Header{
+				Version:        2,
+				PayloadType:    8,
+				SequenceNumber: unit.RTPPackets[0].SequenceNumber,
+				SSRC:           unit.RTPPackets[0].SSRC,
+			},
+			Payload: []byte{1, 2, 3, 4},
+		}}, unit.RTPPackets)
+	})
+
+	t.Run("mulaw", func(t *testing.T) {
+		forma := &format.G711{
+			MULaw: true,
+		}
+
+		p, err := New(1472, forma, true)
+		require.NoError(t, err)
+
+		unit := &unit.G711{
+			Samples: []byte{1, 2, 3, 4},
+		}
+
+		err = p.ProcessUnit(unit)
+		require.NoError(t, err)
+		require.Equal(t, []*rtp.Packet{{
+			Header: rtp.Header{
+				Version:        2,
+				PayloadType:    0,
+				SequenceNumber: unit.RTPPackets[0].SequenceNumber,
+				SSRC:           unit.RTPPackets[0].SSRC,
+			},
+			Payload: []byte{1, 2, 3, 4},
+		}}, unit.RTPPackets)
+	})
+}

internal/formatprocessor/h264.go

@@ -224,13 +224,12 @@ func (t *formatProcessorH264) ProcessUnit(uu unit.Unit) error {
 		if err != nil {
 			return err
 		}
+		u.RTPPackets = pkts
 
 		ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-		for _, pkt := range pkts {
+		for _, pkt := range u.RTPPackets {
 			pkt.Timestamp += ts
 		}
-
-		u.RTPPackets = pkts
 	}
 
 	return nil
@@ -306,12 +305,11 @@ func (t *formatProcessorH264) ProcessRTPPacket( //nolint:dupl
 		if err != nil {
 			return nil, err
 		}
+		u.RTPPackets = pkts
 
-		for _, newPKT := range pkts {
+		for _, newPKT := range u.RTPPackets {
 			newPKT.Timestamp = pkt.Timestamp
 		}
-
-		u.RTPPackets = pkts
 	}
 
 	return u, nil

internal/formatprocessor/h265.go

@@ -243,13 +243,12 @@ func (t *formatProcessorH265) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 		if err != nil {
 			return err
 		}
+		u.RTPPackets = pkts
 
 		ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-		for _, pkt := range pkts {
+		for _, pkt := range u.RTPPackets {
 			pkt.Timestamp += ts
 		}
-
-		u.RTPPackets = pkts
 	}
 
 	return nil
@@ -325,12 +324,11 @@ func (t *formatProcessorH265) ProcessRTPPacket( //nolint:dupl
 		if err != nil {
 			return nil, err
 		}
+		u.RTPPackets = pkts
 
-		for _, newPKT := range pkts {
+		for _, newPKT := range u.RTPPackets {
 			newPKT.Timestamp = pkt.Timestamp
 		}
-
-		u.RTPPackets = pkts
 	}
 
 	return u, nil

internal/formatprocessor/lpcm.go

@@ -41,6 +41,9 @@ func newLPCM(
 func (t *formatProcessorLPCM) createEncoder() error {
 	t.encoder = &rtplpcm.Encoder{
 		PayloadMaxSize: t.udpMaxPayloadSize - 12,
+		PayloadType:    t.format.PayloadTyp,
+		BitDepth:       t.format.BitDepth,
+		ChannelCount:   t.format.ChannelCount,
 	}
 	return t.encoder.Init()
 }
@@ -52,14 +55,13 @@ func (t *formatProcessorLPCM) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/lpcm_test.go

@@ -0,0 +1,37 @@
+package formatprocessor
+
+import (
+	"testing"
+
+	"github.com/bluenviron/gortsplib/v4/pkg/format"
+	"github.com/bluenviron/mediamtx/internal/unit"
+	"github.com/pion/rtp"
+	"github.com/stretchr/testify/require"
+)
+
+func TestLPCMEncode(t *testing.T) {
+	forma := &format.LPCM{
+		PayloadTyp:   96,
+		BitDepth:     16,
+		ChannelCount: 2,
+	}
+
+	p, err := New(1472, forma, true)
+	require.NoError(t, err)
+
+	unit := &unit.LPCM{
+		Samples: []byte{1, 2, 3, 4},
+	}
+
+	err = p.ProcessUnit(unit)
+	require.NoError(t, err)
+	require.Equal(t, []*rtp.Packet{{
+		Header: rtp.Header{
+			Version:        2,
+			PayloadType:    96,
+			SequenceNumber: unit.RTPPackets[0].SequenceNumber,
+			SSRC:           unit.RTPPackets[0].SSRC,
+		},
+		Payload: []byte{1, 2, 3, 4},
+	}}, unit.RTPPackets)
+}

internal/formatprocessor/mjpeg.go

@@ -54,14 +54,13 @@ func (t *formatProcessorMJPEG) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/mpeg1_audio.go

@@ -53,14 +53,13 @@ func (t *formatProcessorMPEG1Audio) ProcessUnit(uu unit.Unit) error { //nolint:d
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/mpeg1_video.go

@@ -54,14 +54,13 @@ func (t *formatProcessorMPEG1Video) ProcessUnit(uu unit.Unit) error { //nolint:d
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/mpeg4_audio.go

@@ -57,14 +57,13 @@ func (t *formatProcessorMPEG4Audio) ProcessUnit(uu unit.Unit) error { //nolint:d
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }
 

internal/formatprocessor/mpeg4_video.go

@@ -94,7 +94,7 @@ func (t *formatProcessorMPEG4Video) ProcessUnit(uu unit.Unit) error { //nolint:d
 		}
 
 		ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-		for _, pkt := range pkts {
+		for _, pkt := range u.RTPPackets {
 			pkt.Timestamp += ts
 		}
 

internal/formatprocessor/vp8.go

@@ -54,14 +54,13 @@ func (t *formatProcessorVP8) ProcessUnit(uu unit.Unit) error { //nolint:dupl
 	if err != nil {
 		return err
 	}
+	u.RTPPackets = pkts
 
 	ts := uint32(multiplyAndDivide(u.PTS, time.Duration(t.format.ClockRate()), time.Second))
-	for _, pkt := range pkts {
+	for _, pkt := range u.RTPPackets {
 		pkt.Timestamp += ts
 	}
 
-	u.RTPPackets = pkts
-
 	return nil
 }