Bump patch

* Fix CTS=0 in fragmented fMP4 with multiple tracks

When muxing fragmented MP4 with both video and audio tracks,
compositionTimeOffset (CTS) was zero for all video samples, causing
B-frame content to display in decode order instead of presentation
order (visible judder).

Root cause: During finalize(), interleaveSamples(true) triggers
finalizeFragment() via the cross-track keyframe check in
addSampleToTrack. This writes the trun box before processTimestamps
has computed correct decodeTimestamp values, so CTS = PTS - DTS = 0.

Fix: Call processTimestamps() for all tracks at the start of
finalizeFragment(). This is safe because processTimestamps is a no-op
when the timestampProcessingQueue is empty.

Video-only fragmented muxing was unaffected because the single-track
case never triggers the cross-track keyframe check during
interleaveSamples.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

* Fix the problem at the actual root

* Oopsie doopsie

---------

Co-authored-by: Claude Opus 4.6 <[email protected]>
Co-authored-by: Vanilagy <[email protected]>

dev/convert.html

@@ -26,7 +26,7 @@
 			chunked: true,
 			chunkSize: 2**20
 		});
-		const outputFormat = new Mediabunny.Mp4OutputFormat({});
+		const outputFormat = new Mediabunny.Mp4OutputFormat({fastStart: 'fragmented'});
 
 		const button = document.createElement('button');
 		button.textContent = 'Cancel';

dev/demux.html

@@ -18,10 +18,11 @@
 		});
 
 		const videoTrack = await input.getPrimaryVideoTrack();
-		const sink = new Mediabunny.VideoSampleSink(videoTrack);
+		const sink = new Mediabunny.EncodedPacketSink(videoTrack);
 
-		const sample = await sink.getSample(await videoTrack.getFirstTimestamp());
+		for await (const packet of sink.packets()) {
-		console.log(sample);
+			console.log(packet.timestamp);
+		}
 
 		/*
 		

dev/live.html

@@ -19,7 +19,7 @@
     button.addEventListener('click', async () => {
         const stream = await navigator.mediaDevices.getDisplayMedia({ video: true, audio: false });
         const videoTrack = stream.getVideoTracks()[0];
-        const audioTrack = null;//stream.getAudioTracks()[0];
+        const audioTrack = stream.getAudioTracks()[0];
 
         const output = new Mediabunny.Output({
             target: new Mediabunny.BufferTarget(),
@@ -29,7 +29,7 @@
 		let audioSource = null;
         if (videoTrack) {
             videoSource = new Mediabunny.MediaStreamVideoTrackSource(videoTrack, {
-                codec: 'avc',
+                codec: 'vp9',
                 bitrate: Mediabunny.QUALITY_MEDIUM,
 				sizeChangeBehavior: 'passThrough',
             });
@@ -40,13 +40,13 @@
         }
         if (audioTrack) {
             audioSource = new Mediabunny.MediaStreamAudioTrackSource(audioTrack, {
-                codec: 'mp3',
+                codec: 'opus',
                 bitrate: Mediabunny.QUALITY_MEDIUM
             });
 
             audioSource.errorPromise.catch((d) => console.log("Hello!!???", d));
 
-            //output.addAudioTrack(audioSource);
+            output.addAudioTrack(audioSource);
         }
 
         await output.start();

docs/.vitepress/config.mts

@@ -17,6 +17,7 @@ export default withMermaid({
 	sitemap: {
 		hostname: 'https://mediabunny.dev',
 	},
+	lastUpdated: true,
 	head: [
 		['link', { rel: 'icon', type: 'image/png', href: '/mediabunny-logo.png' }],
 		['link', { rel: 'icon', type: 'image/svg+xml', href: '/mediabunny-logo.svg' }],

docs/guide/media-sinks.md

@@ -97,9 +97,13 @@ await sink.getKeyPacket(5); // => EncodedPacket | null
 
 When retrieving a packet using a timestamp, the last packet (in [presentation order](#decode-vs-presentation-order)) with a timestamp less than or equal to the search timestamp will be returned. The methods return `null` if there exists no such packet.
 
-There is a special method for retrieving the first packet (in [decode order](#decode-vs-presentation-order)):
+There are special methods for retrieving the first packet (in [decode order](#decode-vs-presentation-order)):
 ```ts
 await sink.getFirstPacket(); // => EncodedPacket | null
+
+// The first packet is typically a key frame, but this is not required.
+// This method returns the first key frame:
+await sink.getFirstKeyPacket(); // => EncodedPacket | null
 ```
 The last packet (in [presentation order](#decode-vs-presentation-order)) can be retrieved like so:
 ```ts

docs/public/robots.txt

@@ -0,0 +1,4 @@
+User-agent: *
+Allow: /
+
+Sitemap: https://mediabunny.dev/sitemap.xml

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "mediabunny",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "mediabunny",
-      "version": "1.38.0",
+      "version": "1.39.1",
       "license": "MPL-2.0",
       "workspaces": [
         "packages/*"
@@ -7751,9 +7751,9 @@
       }
     },
     "node_modules/mediabunny": {
-      "version": "1.37.0",
+      "version": "1.39.0",
-      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.37.0.tgz",
+      "resolved": "https://registry.npmjs.org/mediabunny/-/mediabunny-1.39.0.tgz",
-      "integrity": "sha512-eV7M9IJ29pr/8RNL1sYtIxNbdMfDMN1hMwMaOFfNLhwuKKGSC+eKwiJFpdVjEJ3zrMA4LGerF4Hps0SENFSAlg==",
+      "integrity": "sha512-NDeht2Sf7kYfrUu7b/9AhVK4KdQhy6UeTF/EPNXW+PdpIYvSv36ZQ/SRBoFAJN2LRl6XrGb8JYY4MCnhsGQ2yg==",
       "license": "MPL-2.0",
       "peer": true,
       "workspaces": [
@@ -12077,7 +12077,7 @@
     },
     "packages/aac-encoder": {
       "name": "@mediabunny/aac-encoder",
-      "version": "1.38.0",
+      "version": "1.39.1",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"
@@ -12092,7 +12092,7 @@
     },
     "packages/ac3": {
       "name": "@mediabunny/ac3",
-      "version": "1.38.0",
+      "version": "1.39.1",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"
@@ -12107,7 +12107,7 @@
     },
     "packages/flac-encoder": {
       "name": "@mediabunny/flac-encoder",
-      "version": "1.38.0",
+      "version": "1.39.1",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"
@@ -12122,7 +12122,7 @@
     },
     "packages/mp3-encoder": {
       "name": "@mediabunny/mp3-encoder",
-      "version": "1.38.0",
+      "version": "1.39.1",
       "license": "MPL-2.0",
       "devDependencies": {
         "@types/emscripten": "^1.40.1"

package.json

@@ -1,7 +1,7 @@
 {
   "name": "mediabunny",
   "author": "Vanilagy",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "description": "Pure TypeScript media toolkit for reading, writing, and converting media files, directly in the browser.",
   "type": "module",
   "workspaces": [

packages/aac-encoder/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mediabunny/aac-encoder",
   "author": "Vanilagy",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "description": "AAC encoder extension for Mediabunny, based on FFmpeg.",
   "main": "./dist/bundles/mediabunny-aac-encoder.mjs",
   "module": "./dist/bundles/mediabunny-aac-encoder.mjs",

packages/ac3/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mediabunny/ac3",
   "author": "Vanilagy",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "description": "AC-3 and E-AC-3 (Dolby Digital) decoder and encoder extension for Mediabunny, based on FFmpeg.",
   "main": "./dist/bundles/mediabunny-ac3.mjs",
   "module": "./dist/bundles/mediabunny-ac3.mjs",

packages/flac-encoder/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mediabunny/flac-encoder",
   "author": "Vanilagy",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "description": "FLAC encoder extension for Mediabunny, based on libFLAC.",
   "main": "./dist/bundles/mediabunny-flac-encoder.mjs",
   "module": "./dist/bundles/mediabunny-flac-encoder.mjs",

packages/mp3-encoder/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@mediabunny/mp3-encoder",
   "author": "Vanilagy",
-  "version": "1.38.0",
+  "version": "1.39.1",
   "description": "MP3 encoder extension for Mediabunny, based on LAME.",
   "main": "./dist/bundles/mediabunny-mp3-encoder.mjs",
   "module": "./dist/bundles/mediabunny-mp3-encoder.mjs",

src/conversion.ts

@@ -515,6 +515,9 @@ export class Conversion {
 	/**
 	 * Whether this conversion, as it has been configured, is valid and can be executed. If this field is `false`, check
 	 * the `discardedTracks` field for reasons.
+	 *
+	 * Note: a conversion having discarded tracks does not automatically mean it is invalid; if the remaining, utilized
+	 * tracks make for a valid output file, the conversion is still allowed.
 	 */
 	isValid = false;
 	/** The list of tracks that are included in the output file. */

src/isobmff/isobmff-muxer.ts

@@ -1245,11 +1245,13 @@ export class IsobmffMuxer extends Muxer {
 	override async onTrackClose(track: OutputTrack) {
 		const release = await this.mutex.acquire();
 
-		if (track.type === 'subtitle' && track.source._codec === 'webvtt') {
+		const trackData = this.trackDatas.find(x => x.track === track);
-			const trackData = this.trackDatas.find(x => x.track === track) as IsobmffSubtitleTrackData;
+		if (trackData) {
-			if (trackData) {
+			if (trackData.type === 'subtitle' && track.source._codec === 'webvtt') {
 				await this.processWebVTTCues(trackData, Infinity);
 			}
+
+			this.processTimestamps(trackData);
 		}
 
 		if (this.allTracksAreKnown()) {
@@ -1274,19 +1276,15 @@ export class IsobmffMuxer extends Muxer {
 			if (trackData.type === 'subtitle' && trackData.track.source._codec === 'webvtt') {
 				await this.processWebVTTCues(trackData, Infinity);
 			}
+
+			this.processTimestamps(trackData);
 		}
 
 		if (this.isFragmented) {
 			await this.interleaveSamples(true);
-
-			for (const trackData of this.trackDatas) {
-				this.processTimestamps(trackData);
-			}
-
 			await this.finalizeFragment(false); // Don't flush the last fragment as we will flush it with the mfra box
 		} else {
 			for (const trackData of this.trackDatas) {
-				this.processTimestamps(trackData);
 				await this.finalizeCurrentChunk(trackData);
 			}
 		}

src/media-sink.ts

@@ -144,6 +144,23 @@ export class EncodedPacketSink {
 		return maybeFixPacketType(this._track, this._track._backing.getFirstPacket(options), options);
 	}
 
+	/** Retrieves the track's first key packet (in decode order), or null if it has no key packets. */
+	async getFirstKeyPacket(options: PacketRetrievalOptions = {}) {
+		validatePacketRetrievalOptions(options);
+
+		const firstPacket = await this.getFirstPacket(options);
+		if (!firstPacket) {
+			return null;
+		}
+
+		if (firstPacket.type === 'key') {
+			// Great
+			return firstPacket;
+		}
+
+		return this.getNextKeyPacket(firstPacket, options);
+	}
+
 	/**
 	 * Retrieves the packet corresponding to the given timestamp, in seconds. More specifically, returns the last packet
 	 * (in presentation order) with a start timestamp less than or equal to the given timestamp. This method can be
@@ -476,7 +493,7 @@ export abstract class BaseMediaSampleSink<
 
 			const packetSink = this._createPacketSink();
 			const keyPacket = await packetSink.getKeyPacket(startTimestamp, { verifyKeyPackets: true })
-				?? await packetSink.getFirstPacket();
+				?? await packetSink.getFirstKeyPacket({ verifyKeyPackets: true });
 
 			let currentPacket: EncodedPacket | null = keyPacket;
 

src/media-source.ts

@@ -1076,6 +1076,8 @@ export class MediaStreamVideoTrackSource extends VideoSource {
 	private _lastVideoFrame: VideoFrame | null = null;
 	/** @internal */
 	private _timerHandle: UnthrottledTimerHandle | null = null;
+	/** @internal */
+	private _videoElement: HTMLVideoElement | null = null;
 
 	/** A promise that rejects upon any error within this source. This promise never resolves. */
 	get errorPromise() {
@@ -1160,12 +1162,13 @@ export class MediaStreamVideoTrackSource extends VideoSource {
 			while (now - lastFrameTime > 1000 / frameRate) {
 				lastFrameTime += 1000 / frameRate;
 				const timestamp = firstVideoFrameTimestamp + frameCount / frameRate;
-				const clone = new VideoFrame(this._lastVideoFrame, {
+
+				const frame = new VideoFrame(this._videoElement ?? this._lastVideoFrame, {
 					timestamp: 1e6 * timestamp,
 					duration: 1e6 / frameRate,
 				});
 
-				addVideoFrame(clone, now);
+				addVideoFrame(frame, now);
 			}
 		};
 
@@ -1298,8 +1301,44 @@ export class MediaStreamVideoTrackSource extends VideoSource {
 				};
 
 				mediaStreamTrackProcessorWorker!.addEventListener('message', this._workerListener);
+			} else if (frameRate !== null) {
+				// No MediaStreamTrackProcessor support at all (e.g. Firefox), but we have a frame rate, so we can
+				// manually sample from a hidden <video> element instead.
+				const video = document.createElement('video');
+				video.style.position = 'fixed';
+				video.style.left = '-10000px';
+				video.style.top = '-10000px';
+				video.style.width = '1px';
+				video.style.height = '1px';
+				video.style.opacity = '0';
+				video.style.pointerEvents = 'none';
+				video.muted = true;
+				video.srcObject = new MediaStream([this._track]);
+				document.body.appendChild(video);
+				this._videoElement = video;
+
+				video.addEventListener('loadeddata', () => {
+					if (errored || !this._videoElement) {
+						return;
+					}
+
+					// This will be the first frame
+					const frame = new VideoFrame(video, {
+						timestamp: 1000 * performance.now(),
+					});
+					onVideoFrame(frame);
+					frame.close();
+				}, { once: true });
+
+				void video.play().catch((error) => {
+					errored = true;
+					this._promiseWithResolvers.reject(error);
+				});
 			} else {
-				throw new Error('MediaStreamTrackProcessor is required but not supported by this browser.');
+				throw new Error(
+					'When no explicit frame rate is set, MediaStreamTrackProcessor is required; but it\'s not supported'
+					+ ' by this browser.',
+				);
 			}
 		}
 	}
@@ -1329,6 +1368,12 @@ export class MediaStreamVideoTrackSource extends VideoSource {
 		}
 		this._lastVideoFrame?.close();
 
+		if (this._videoElement) {
+			this._videoElement.srcObject = null;
+			this._videoElement.remove();
+			this._videoElement = null;
+		}
+
 		if (this._workerTrackId !== null) {
 			assert(this._workerListener);
 

test/node/isobmff-muxer.test.ts

@@ -61,3 +61,46 @@ test('ISOBMFF muxer internally converts ADTS to AAC', async () => {
 
 	expect(count).toBe(4557);
 });
+
+test('Fragmented fMP4 with video+audio preserves B-frame CTS', async () => {
+	using input = new Input({
+		source: new FilePathSource(path.join(__dirname, '../public/video.mp4')),
+		formats: ALL_FORMATS,
+	});
+
+	const videoTrack = await input.getPrimaryVideoTrack();
+	const audioTrack = await input.getPrimaryAudioTrack();
+	assert(videoTrack);
+	assert(audioTrack);
+
+	const originalVideoSink = new EncodedPacketSink(videoTrack);
+	const originalTimestamps: number[] = [];
+	for await (const packet of originalVideoSink.packets()) {
+		originalTimestamps.push(packet.timestamp);
+	}
+
+	const output = new Output({
+		format: new Mp4OutputFormat({ fastStart: 'fragmented' }),
+		target: new BufferTarget(),
+	});
+
+	const conversion = await Conversion.init({ input, output, showWarnings: false });
+	await conversion.execute();
+
+	using outputAsInput = new Input({
+		source: new BufferSource(output.target.buffer!),
+		formats: ALL_FORMATS,
+	});
+
+	const outputVideoTrack = await outputAsInput.getPrimaryVideoTrack();
+	assert(outputVideoTrack);
+
+	const videoSink = new EncodedPacketSink(outputVideoTrack);
+
+	const timestamps: number[] = [];
+	for await (const packet of videoSink.packets()) {
+		timestamps.push(packet.timestamp);
+	}
+
+	expect(timestamps).toEqual(originalTimestamps);
+});