mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-09-03 12:54:29 +00:00
test(engine): give the real-ffmpeg audio suites a timeout Windows can meet
`Tests on windows-latest` failed on two of the seven cases in audioMixer.grouping.test.ts -- both `Test timed out in 5000ms`, not an assertion. Every case in that suite mixes with REAL ffmpeg, and vitest's default 5s per test is not enough for that on a Windows runner: the same suite passes on macOS and ubuntu, and the job's own "Install FFmpeg" step logged a download-failure warning before falling back. A suite-level 60s covers all seven at once rather than seven per-test arguments. audioMixer.level.test.ts gets the same treatment. It has not failed yet, but it is the same real-ffmpeg shape one spawn slower away from it. Both files are this branch's, so this is the branch's own flake to fix; engine has no existing per-test timeout convention to follow, hence the suite argument plus a comment saying which platform forced it.
This commit is contained in:
Vance Ingalls
@@ -103,294 +103,301 @@ const track = (id: string, end: number, volume = 1) => ({
|
||||
type: "audio" as const,
|
||||
});
|
||||
|
||||
describe.skipIf(!HAS_FFMPEG)("mix level arithmetic", () => {
|
||||
afterEach(() => {
|
||||
for (const dir of tempDirs.splice(0)) rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it("keeps every track at its authored level regardless of how many there are", async () => {
|
||||
// The property the compensation exists to hold: adding tracks must not
|
||||
// duck the ones already there. Mixing the SAME tone twice is the cleanest
|
||||
// probe — two coherent copies sum to exactly +6.02 dB, so any residual
|
||||
// normalisation shows up as a plain arithmetic miss rather than something
|
||||
// that has to be teased out of unrelated material.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-count-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-count-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "a.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "b.wav"), 440, 2, 0.4);
|
||||
const oneUp = join(projectDir, `one-${MIXED_AUDIO_FILENAME}`);
|
||||
const twoUp = join(projectDir, `two-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const one = await processCompositionAudio([track("a", 2)], projectDir, workDir, oneUp, 2);
|
||||
const two = await processCompositionAudio(
|
||||
[track("a", 2), track("b", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
twoUp,
|
||||
2,
|
||||
);
|
||||
expect(one.success).toBe(true);
|
||||
expect(two.success).toBe(true);
|
||||
|
||||
// Two coherent copies of one tone = +6.02 dB. If amix's 1/N ever survives
|
||||
// the correction, this lands at 0 dB instead.
|
||||
expect(meanVolumeDb(twoUp) - meanVolumeDb(oneUp)).toBeCloseTo(6.02, 0);
|
||||
});
|
||||
|
||||
it("does not lift the survivors when a shorter track ends", async () => {
|
||||
// amix with normalize=true rescales by the number of CURRENTLY ACTIVE
|
||||
// inputs, so a track ending mid-composition would hand the remaining ones
|
||||
// a level jump. `apad` to the full duration is what holds every input
|
||||
// active for the whole graph and neutralises that — an invariant the
|
||||
// filter string relies on without saying so.
|
||||
//
|
||||
// Measured without apad (spike, 2026-08-14): the tail runs +1.94 dB hot.
|
||||
// Any group work that builds its own amix has to keep the padding, or
|
||||
// inherit that bug one level down.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-drop-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-drop-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "short.wav"), 440, 1, 0.5);
|
||||
writeTone(join(projectDir, "long.wav"), 880, 3, 0.5);
|
||||
const together = join(projectDir, `both-${MIXED_AUDIO_FILENAME}`);
|
||||
const alone = join(projectDir, `alone-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const both = await processCompositionAudio(
|
||||
[track("short", 1), track("long", 3)],
|
||||
projectDir,
|
||||
workDir,
|
||||
together,
|
||||
3,
|
||||
);
|
||||
const solo = await processCompositionAudio([track("long", 3)], projectDir, workDir, alone, 3);
|
||||
expect(both.success).toBe(true);
|
||||
expect(solo.success).toBe(true);
|
||||
|
||||
// After 1.5 s only `long` is sounding. It must read the same whether or not
|
||||
// a second track happened to end earlier.
|
||||
const tailTogether = meanVolumeDb(together, 1.5, 3);
|
||||
const tailAlone = meanVolumeDb(alone, 1.5, 3);
|
||||
expect(Math.abs(tailTogether - tailAlone)).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
/**
|
||||
* The gate for group buses (plans/audio-mixer-groups.md §1).
|
||||
*
|
||||
* Grouping is routing, not processing: a group whose FX chain is empty must
|
||||
* be a no-op on the mix. Enable this the moment `data-audio-group` routes
|
||||
* through a nested amix — it is the definition of done for §1.3, and the
|
||||
* only thing standing between a wrong gain correction and a silently loud
|
||||
* export.
|
||||
*
|
||||
* Proven reachable in the spike: nesting with each amix compensated by ITS
|
||||
* OWN input count nulls against the flat mix to -inf (sample-identical), as
|
||||
* does `amix=normalize=0` with no correction at all.
|
||||
*/
|
||||
it("mixes a grouped composition at the same level as the ungrouped one", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-level-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-level-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "a.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "b.wav"), 660, 2, 0.4);
|
||||
const flatOut = join(projectDir, `flat-${MIXED_AUDIO_FILENAME}`);
|
||||
const groupedOut = join(projectDir, `grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const flat = await processCompositionAudio(
|
||||
[track("a", 2), track("b", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
flatOut,
|
||||
2,
|
||||
);
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "voiceover" },
|
||||
{ ...track("b", 2), groupId: "voiceover" },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
expect(flat.success).toBe(true);
|
||||
expect(grouped.success).toBe(true);
|
||||
|
||||
// An empty group chain is pure routing — the export must read the same
|
||||
// whether or not the two tones happened to share a group.
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(flatOut))).toBeLessThan(0.3);
|
||||
});
|
||||
|
||||
it("a group FX chain fully cutting its members leaves an ungrouped track untouched (routing isolation)", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-fx-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-fx-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "voice.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "sfx.wav"), 880, 2, 0.4);
|
||||
const mixedOut = join(projectDir, `mixed-${MIXED_AUDIO_FILENAME}`);
|
||||
const sfxAloneOut = join(projectDir, `sfx-alone-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const groupChain = JSON.stringify({
|
||||
version: 1,
|
||||
nodes: [{ type: "gain", id: "g", params: { gain: -60 } }],
|
||||
// Every case here mixes with REAL ffmpeg, and vitest's default 5s per test is not
|
||||
// enough for that on a Windows runner — two cases timed out there while passing
|
||||
// everywhere else (PR #3363). The suite-level timeout covers all of them at once.
|
||||
describe.skipIf(!HAS_FFMPEG)(
|
||||
"mix level arithmetic",
|
||||
() => {
|
||||
afterEach(() => {
|
||||
for (const dir of tempDirs.splice(0)) rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
const mixed = await processCompositionAudio(
|
||||
[{ ...track("voice", 2), groupId: "vo", groupFxChain: groupChain }, track("sfx", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
mixedOut,
|
||||
2,
|
||||
);
|
||||
const sfxAlone = await processCompositionAudio(
|
||||
[track("sfx", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
sfxAloneOut,
|
||||
2,
|
||||
);
|
||||
expect(mixed.success).toBe(true);
|
||||
expect(sfxAlone.success).toBe(true);
|
||||
it("keeps every track at its authored level regardless of how many there are", async () => {
|
||||
// The property the compensation exists to hold: adding tracks must not
|
||||
// duck the ones already there. Mixing the SAME tone twice is the cleanest
|
||||
// probe — two coherent copies sum to exactly +6.02 dB, so any residual
|
||||
// normalisation shows up as a plain arithmetic miss rather than something
|
||||
// that has to be teased out of unrelated material.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-count-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-count-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
// The voice group is cut ~60 dB — the mix should read close to sfx alone,
|
||||
// and the ungrouped sfx track's own processing is unaffected by the
|
||||
// group existing at all.
|
||||
expect(Math.abs(meanVolumeDb(mixedOut) - meanVolumeDb(sfxAloneOut))).toBeLessThan(0.5);
|
||||
});
|
||||
writeTone(join(projectDir, "a.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "b.wav"), 440, 2, 0.4);
|
||||
const oneUp = join(projectDir, `one-${MIXED_AUDIO_FILENAME}`);
|
||||
const twoUp = join(projectDir, `two-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
it("a member's own volume envelope still applies inside a group", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-env-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-env-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
const one = await processCompositionAudio([track("a", 2)], projectDir, workDir, oneUp, 2);
|
||||
const two = await processCompositionAudio(
|
||||
[track("a", 2), track("b", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
twoUp,
|
||||
2,
|
||||
);
|
||||
expect(one.success).toBe(true);
|
||||
expect(two.success).toBe(true);
|
||||
|
||||
writeTone(join(projectDir, "a.wav"), 440, 4, 0.5);
|
||||
const groupedOut = join(projectDir, `grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const flatOut = join(projectDir, `flat-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const withEnvelope = {
|
||||
...track("a", 4),
|
||||
volumeKeyframes: [
|
||||
{ time: 0, volume: 1 },
|
||||
{ time: 4, volume: 0 },
|
||||
],
|
||||
};
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[{ ...withEnvelope, groupId: "vo" }],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
4,
|
||||
);
|
||||
const flat = await processCompositionAudio([withEnvelope], projectDir, workDir, flatOut, 4);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(flat.success).toBe(true);
|
||||
|
||||
// The envelope fades to silent — the tail should read the same whether
|
||||
// the track is grouped or not, proving member-level processing survives
|
||||
// the group path unchanged.
|
||||
const groupedTail = meanVolumeDb(groupedOut, 3, 4);
|
||||
const flatTail = meanVolumeDb(flatOut, 3, 4);
|
||||
expect(Math.abs(groupedTail - flatTail)).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
// Members sum at unity (normalize=0), so an over-unity sum used to hard-clip
|
||||
// at ±1 in the 16-bit intermediate BEFORE the group's fader and FX chain ran
|
||||
// — pulling the group down then operated on distortion. Every existing probe
|
||||
// here sums to ≤ 0.8, which is exactly why nothing caught it; preview cannot
|
||||
// reproduce it either, because its bus is float.
|
||||
it("does not clip an over-unity member sum before the group fader", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-clip-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-clip-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
// Two coherent copies of the same tone: 0.7 + 0.7 = 1.4, comfortably over.
|
||||
// `writePeakTone`, not `writeTone` — ffmpeg's `sine` source is nowhere near
|
||||
// full scale (its output peaks at ~0.125), so every tone in this file sits
|
||||
// around -21 dBFS and NOTHING here can reach a clip no matter what gain is
|
||||
// asked for. That is a large part of why this class of bug survived.
|
||||
writePeakTone(join(projectDir, "a.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "b.wav"), 440, 2, 0.7);
|
||||
// The reference: the level that sum SHOULD reach once the group's 0.5
|
||||
// fader has been applied — 1.4 × 0.5 = 0.7, one tone's worth.
|
||||
writePeakTone(join(projectDir, "ref.wav"), 440, 2, 0.7);
|
||||
|
||||
const groupedOut = join(projectDir, `clip-grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const refOut = join(projectDir, `clip-ref-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "vo", groupVolume: 0.5 },
|
||||
{ ...track("b", 2), groupId: "vo", groupVolume: 0.5 },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
const reference = await processCompositionAudio(
|
||||
[track("ref", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
refOut,
|
||||
2,
|
||||
);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(reference.success).toBe(true);
|
||||
|
||||
// Both are ONE track into the outer mix, so the outer graph is identical
|
||||
// and the levels are directly comparable. Clipped, the flat-topped sum
|
||||
// reads well over a dB hot even after the fader halves it.
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(refOut))).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
// The same property, for a group that carries an FX CHAIN. That path runs the
|
||||
// sum through applyAudioFxChain, whose writeWav clamps to ±1 and emits 16-bit
|
||||
// — so the headroom the float sub-mix preserved was handed back before the
|
||||
// fader, one step later than the original bug but with the same result.
|
||||
// A transparent chain isolates the clamp from anything the effects do.
|
||||
it("does not clip an over-unity sum before the fader when the group has FX", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-clipfx-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-clipfx-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writePeakTone(join(projectDir, "a.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "b.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "ref.wav"), 440, 2, 0.7);
|
||||
|
||||
// 0 dB gain: in the chain, doing nothing to the level.
|
||||
const transparentChain = JSON.stringify({
|
||||
version: 1,
|
||||
nodes: [{ type: "gain", id: "g", params: { gain: 0 } }],
|
||||
// Two coherent copies of one tone = +6.02 dB. If amix's 1/N ever survives
|
||||
// the correction, this lands at 0 dB instead.
|
||||
expect(meanVolumeDb(twoUp) - meanVolumeDb(oneUp)).toBeCloseTo(6.02, 0);
|
||||
});
|
||||
|
||||
const groupedOut = join(projectDir, `clipfx-grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const refOut = join(projectDir, `clipfx-ref-${MIXED_AUDIO_FILENAME}`);
|
||||
it("does not lift the survivors when a shorter track ends", async () => {
|
||||
// amix with normalize=true rescales by the number of CURRENTLY ACTIVE
|
||||
// inputs, so a track ending mid-composition would hand the remaining ones
|
||||
// a level jump. `apad` to the full duration is what holds every input
|
||||
// active for the whole graph and neutralises that — an invariant the
|
||||
// filter string relies on without saying so.
|
||||
//
|
||||
// Measured without apad (spike, 2026-08-14): the tail runs +1.94 dB hot.
|
||||
// Any group work that builds its own amix has to keep the padding, or
|
||||
// inherit that bug one level down.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-drop-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-drop-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "vo", groupVolume: 0.5, groupFxChain: transparentChain },
|
||||
{ ...track("b", 2), groupId: "vo", groupVolume: 0.5, groupFxChain: transparentChain },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
const reference = await processCompositionAudio(
|
||||
[track("ref", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
refOut,
|
||||
2,
|
||||
);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(reference.success).toBe(true);
|
||||
writeTone(join(projectDir, "short.wav"), 440, 1, 0.5);
|
||||
writeTone(join(projectDir, "long.wav"), 880, 3, 0.5);
|
||||
const together = join(projectDir, `both-${MIXED_AUDIO_FILENAME}`);
|
||||
const alone = join(projectDir, `alone-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(refOut))).toBeLessThan(0.5);
|
||||
});
|
||||
});
|
||||
const both = await processCompositionAudio(
|
||||
[track("short", 1), track("long", 3)],
|
||||
projectDir,
|
||||
workDir,
|
||||
together,
|
||||
3,
|
||||
);
|
||||
const solo = await processCompositionAudio([track("long", 3)], projectDir, workDir, alone, 3);
|
||||
expect(both.success).toBe(true);
|
||||
expect(solo.success).toBe(true);
|
||||
|
||||
// After 1.5 s only `long` is sounding. It must read the same whether or not
|
||||
// a second track happened to end earlier.
|
||||
const tailTogether = meanVolumeDb(together, 1.5, 3);
|
||||
const tailAlone = meanVolumeDb(alone, 1.5, 3);
|
||||
expect(Math.abs(tailTogether - tailAlone)).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
/**
|
||||
* The gate for group buses (plans/audio-mixer-groups.md §1).
|
||||
*
|
||||
* Grouping is routing, not processing: a group whose FX chain is empty must
|
||||
* be a no-op on the mix. Enable this the moment `data-audio-group` routes
|
||||
* through a nested amix — it is the definition of done for §1.3, and the
|
||||
* only thing standing between a wrong gain correction and a silently loud
|
||||
* export.
|
||||
*
|
||||
* Proven reachable in the spike: nesting with each amix compensated by ITS
|
||||
* OWN input count nulls against the flat mix to -inf (sample-identical), as
|
||||
* does `amix=normalize=0` with no correction at all.
|
||||
*/
|
||||
it("mixes a grouped composition at the same level as the ungrouped one", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-level-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-level-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "a.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "b.wav"), 660, 2, 0.4);
|
||||
const flatOut = join(projectDir, `flat-${MIXED_AUDIO_FILENAME}`);
|
||||
const groupedOut = join(projectDir, `grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const flat = await processCompositionAudio(
|
||||
[track("a", 2), track("b", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
flatOut,
|
||||
2,
|
||||
);
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "voiceover" },
|
||||
{ ...track("b", 2), groupId: "voiceover" },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
expect(flat.success).toBe(true);
|
||||
expect(grouped.success).toBe(true);
|
||||
|
||||
// An empty group chain is pure routing — the export must read the same
|
||||
// whether or not the two tones happened to share a group.
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(flatOut))).toBeLessThan(0.3);
|
||||
});
|
||||
|
||||
it("a group FX chain fully cutting its members leaves an ungrouped track untouched (routing isolation)", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-fx-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-fx-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "voice.wav"), 440, 2, 0.4);
|
||||
writeTone(join(projectDir, "sfx.wav"), 880, 2, 0.4);
|
||||
const mixedOut = join(projectDir, `mixed-${MIXED_AUDIO_FILENAME}`);
|
||||
const sfxAloneOut = join(projectDir, `sfx-alone-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const groupChain = JSON.stringify({
|
||||
version: 1,
|
||||
nodes: [{ type: "gain", id: "g", params: { gain: -60 } }],
|
||||
});
|
||||
|
||||
const mixed = await processCompositionAudio(
|
||||
[{ ...track("voice", 2), groupId: "vo", groupFxChain: groupChain }, track("sfx", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
mixedOut,
|
||||
2,
|
||||
);
|
||||
const sfxAlone = await processCompositionAudio(
|
||||
[track("sfx", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
sfxAloneOut,
|
||||
2,
|
||||
);
|
||||
expect(mixed.success).toBe(true);
|
||||
expect(sfxAlone.success).toBe(true);
|
||||
|
||||
// The voice group is cut ~60 dB — the mix should read close to sfx alone,
|
||||
// and the ungrouped sfx track's own processing is unaffected by the
|
||||
// group existing at all.
|
||||
expect(Math.abs(meanVolumeDb(mixedOut) - meanVolumeDb(sfxAloneOut))).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
it("a member's own volume envelope still applies inside a group", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-env-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-env-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writeTone(join(projectDir, "a.wav"), 440, 4, 0.5);
|
||||
const groupedOut = join(projectDir, `grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const flatOut = join(projectDir, `flat-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const withEnvelope = {
|
||||
...track("a", 4),
|
||||
volumeKeyframes: [
|
||||
{ time: 0, volume: 1 },
|
||||
{ time: 4, volume: 0 },
|
||||
],
|
||||
};
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[{ ...withEnvelope, groupId: "vo" }],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
4,
|
||||
);
|
||||
const flat = await processCompositionAudio([withEnvelope], projectDir, workDir, flatOut, 4);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(flat.success).toBe(true);
|
||||
|
||||
// The envelope fades to silent — the tail should read the same whether
|
||||
// the track is grouped or not, proving member-level processing survives
|
||||
// the group path unchanged.
|
||||
const groupedTail = meanVolumeDb(groupedOut, 3, 4);
|
||||
const flatTail = meanVolumeDb(flatOut, 3, 4);
|
||||
expect(Math.abs(groupedTail - flatTail)).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
// Members sum at unity (normalize=0), so an over-unity sum used to hard-clip
|
||||
// at ±1 in the 16-bit intermediate BEFORE the group's fader and FX chain ran
|
||||
// — pulling the group down then operated on distortion. Every existing probe
|
||||
// here sums to ≤ 0.8, which is exactly why nothing caught it; preview cannot
|
||||
// reproduce it either, because its bus is float.
|
||||
it("does not clip an over-unity member sum before the group fader", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-clip-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-clip-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
// Two coherent copies of the same tone: 0.7 + 0.7 = 1.4, comfortably over.
|
||||
// `writePeakTone`, not `writeTone` — ffmpeg's `sine` source is nowhere near
|
||||
// full scale (its output peaks at ~0.125), so every tone in this file sits
|
||||
// around -21 dBFS and NOTHING here can reach a clip no matter what gain is
|
||||
// asked for. That is a large part of why this class of bug survived.
|
||||
writePeakTone(join(projectDir, "a.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "b.wav"), 440, 2, 0.7);
|
||||
// The reference: the level that sum SHOULD reach once the group's 0.5
|
||||
// fader has been applied — 1.4 × 0.5 = 0.7, one tone's worth.
|
||||
writePeakTone(join(projectDir, "ref.wav"), 440, 2, 0.7);
|
||||
|
||||
const groupedOut = join(projectDir, `clip-grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const refOut = join(projectDir, `clip-ref-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "vo", groupVolume: 0.5 },
|
||||
{ ...track("b", 2), groupId: "vo", groupVolume: 0.5 },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
const reference = await processCompositionAudio(
|
||||
[track("ref", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
refOut,
|
||||
2,
|
||||
);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(reference.success).toBe(true);
|
||||
|
||||
// Both are ONE track into the outer mix, so the outer graph is identical
|
||||
// and the levels are directly comparable. Clipped, the flat-topped sum
|
||||
// reads well over a dB hot even after the fader halves it.
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(refOut))).toBeLessThan(0.5);
|
||||
});
|
||||
|
||||
// The same property, for a group that carries an FX CHAIN. That path runs the
|
||||
// sum through applyAudioFxChain, whose writeWav clamps to ±1 and emits 16-bit
|
||||
// — so the headroom the float sub-mix preserved was handed back before the
|
||||
// fader, one step later than the original bug but with the same result.
|
||||
// A transparent chain isolates the clamp from anything the effects do.
|
||||
it("does not clip an over-unity sum before the fader when the group has FX", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-grp-clipfx-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-grp-clipfx-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
|
||||
writePeakTone(join(projectDir, "a.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "b.wav"), 440, 2, 0.7);
|
||||
writePeakTone(join(projectDir, "ref.wav"), 440, 2, 0.7);
|
||||
|
||||
// 0 dB gain: in the chain, doing nothing to the level.
|
||||
const transparentChain = JSON.stringify({
|
||||
version: 1,
|
||||
nodes: [{ type: "gain", id: "g", params: { gain: 0 } }],
|
||||
});
|
||||
|
||||
const groupedOut = join(projectDir, `clipfx-grouped-${MIXED_AUDIO_FILENAME}`);
|
||||
const refOut = join(projectDir, `clipfx-ref-${MIXED_AUDIO_FILENAME}`);
|
||||
|
||||
const grouped = await processCompositionAudio(
|
||||
[
|
||||
{ ...track("a", 2), groupId: "vo", groupVolume: 0.5, groupFxChain: transparentChain },
|
||||
{ ...track("b", 2), groupId: "vo", groupVolume: 0.5, groupFxChain: transparentChain },
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
groupedOut,
|
||||
2,
|
||||
);
|
||||
const reference = await processCompositionAudio(
|
||||
[track("ref", 2)],
|
||||
projectDir,
|
||||
workDir,
|
||||
refOut,
|
||||
2,
|
||||
);
|
||||
expect(grouped.success).toBe(true);
|
||||
expect(reference.success).toBe(true);
|
||||
|
||||
expect(Math.abs(meanVolumeDb(groupedOut) - meanVolumeDb(refOut))).toBeLessThan(0.5);
|
||||
});
|
||||
},
|
||||
60_000,
|
||||
);
|
||||
|
||||
@@ -55,110 +55,117 @@ function firstAudibleSeconds(path: string): number {
|
||||
throw new Error(`No audible sample found in ${path}`);
|
||||
}
|
||||
|
||||
describe.skipIf(!HAS_FFMPEG)("processCompositionAudio levels", () => {
|
||||
afterEach(() => {
|
||||
for (const dir of tempDirs.splice(0)) rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
// Same real-ffmpeg exposure as audioMixer.grouping.test.ts, which timed out on a
|
||||
// Windows runner at vitest's default 5s. This one has not failed yet; it is one
|
||||
// spawn slower away from it.
|
||||
describe.skipIf(!HAS_FFMPEG)(
|
||||
"processCompositionAudio levels",
|
||||
() => {
|
||||
afterEach(() => {
|
||||
for (const dir of tempDirs.splice(0)) rmSync(dir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
it("preserves the level of a mono source in the stereo mix", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-mono-level-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-mono-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
const sourcePath = join(projectDir, "voice.wav");
|
||||
const outputPath = join(projectDir, "audio.aac");
|
||||
const setup = spawnSync(
|
||||
getFfmpegBinary(),
|
||||
[
|
||||
"-nostdin",
|
||||
"-v",
|
||||
"error",
|
||||
"-f",
|
||||
"lavfi",
|
||||
"-i",
|
||||
"sine=frequency=1000:duration=1:sample_rate=48000",
|
||||
"-ac",
|
||||
"1",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
sourcePath,
|
||||
],
|
||||
{ encoding: "utf-8" },
|
||||
);
|
||||
expect(setup.status, setup.stderr).toBe(0);
|
||||
it("preserves the level of a mono source in the stereo mix", async () => {
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-mono-level-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-mono-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
const sourcePath = join(projectDir, "voice.wav");
|
||||
const outputPath = join(projectDir, "audio.aac");
|
||||
const setup = spawnSync(
|
||||
getFfmpegBinary(),
|
||||
[
|
||||
"-nostdin",
|
||||
"-v",
|
||||
"error",
|
||||
"-f",
|
||||
"lavfi",
|
||||
"-i",
|
||||
"sine=frequency=1000:duration=1:sample_rate=48000",
|
||||
"-ac",
|
||||
"1",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
sourcePath,
|
||||
],
|
||||
{ encoding: "utf-8" },
|
||||
);
|
||||
expect(setup.status, setup.stderr).toBe(0);
|
||||
|
||||
const result = await processCompositionAudio(
|
||||
[
|
||||
{
|
||||
id: "voice",
|
||||
src: "voice.wav",
|
||||
start: 0,
|
||||
end: 1,
|
||||
mediaStart: 0,
|
||||
layer: 0,
|
||||
volume: 1,
|
||||
type: "audio",
|
||||
},
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
outputPath,
|
||||
1,
|
||||
);
|
||||
const result = await processCompositionAudio(
|
||||
[
|
||||
{
|
||||
id: "voice",
|
||||
src: "voice.wav",
|
||||
start: 0,
|
||||
end: 1,
|
||||
mediaStart: 0,
|
||||
layer: 0,
|
||||
volume: 1,
|
||||
type: "audio",
|
||||
},
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
outputPath,
|
||||
1,
|
||||
);
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(meanVolumeDb(outputPath) - meanVolumeDb(sourcePath)).toBeGreaterThan(-0.3);
|
||||
});
|
||||
expect(result.success).toBe(true);
|
||||
expect(meanVolumeDb(outputPath) - meanVolumeDb(sourcePath)).toBeGreaterThan(-0.3);
|
||||
});
|
||||
|
||||
it("places a delayed track on its authored start, not one AAC frame later", async () => {
|
||||
// The mix is AAC-encoded, and AAC encoders emit ~1024 priming samples. A
|
||||
// raw ADTS container has nowhere to record that delay, so it decodes as
|
||||
// real leading silence and drags the whole track 21.33 ms late against a
|
||||
// frame-accurate video. MIXED_AUDIO_FILENAME picks a container that stores
|
||||
// the delay as an edit list instead; this asserts the artifact we actually
|
||||
// ship lands on time.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-onset-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-onset-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
const sourcePath = join(projectDir, "tone.wav");
|
||||
const outputPath = join(projectDir, MIXED_AUDIO_FILENAME);
|
||||
const setup = spawnSync(
|
||||
getFfmpegBinary(),
|
||||
[
|
||||
"-nostdin",
|
||||
"-v",
|
||||
"error",
|
||||
"-f",
|
||||
"lavfi",
|
||||
"-i",
|
||||
"sine=frequency=1000:duration=1:sample_rate=48000",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
sourcePath,
|
||||
],
|
||||
{ encoding: "utf-8" },
|
||||
);
|
||||
expect(setup.status, setup.stderr).toBe(0);
|
||||
it("places a delayed track on its authored start, not one AAC frame later", async () => {
|
||||
// The mix is AAC-encoded, and AAC encoders emit ~1024 priming samples. A
|
||||
// raw ADTS container has nowhere to record that delay, so it decodes as
|
||||
// real leading silence and drags the whole track 21.33 ms late against a
|
||||
// frame-accurate video. MIXED_AUDIO_FILENAME picks a container that stores
|
||||
// the delay as an edit list instead; this asserts the artifact we actually
|
||||
// ship lands on time.
|
||||
const projectDir = mkdtempSync(join(tmpdir(), "hf-onset-"));
|
||||
const workDir = mkdtempSync(join(tmpdir(), "hf-onset-work-"));
|
||||
tempDirs.push(projectDir, workDir);
|
||||
const sourcePath = join(projectDir, "tone.wav");
|
||||
const outputPath = join(projectDir, MIXED_AUDIO_FILENAME);
|
||||
const setup = spawnSync(
|
||||
getFfmpegBinary(),
|
||||
[
|
||||
"-nostdin",
|
||||
"-v",
|
||||
"error",
|
||||
"-f",
|
||||
"lavfi",
|
||||
"-i",
|
||||
"sine=frequency=1000:duration=1:sample_rate=48000",
|
||||
"-c:a",
|
||||
"pcm_s16le",
|
||||
sourcePath,
|
||||
],
|
||||
{ encoding: "utf-8" },
|
||||
);
|
||||
expect(setup.status, setup.stderr).toBe(0);
|
||||
|
||||
const result = await processCompositionAudio(
|
||||
[
|
||||
{
|
||||
id: "tone",
|
||||
src: "tone.wav",
|
||||
start: 2,
|
||||
end: 3,
|
||||
mediaStart: 0,
|
||||
layer: 0,
|
||||
volume: 1,
|
||||
type: "audio",
|
||||
},
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
outputPath,
|
||||
4,
|
||||
);
|
||||
const result = await processCompositionAudio(
|
||||
[
|
||||
{
|
||||
id: "tone",
|
||||
src: "tone.wav",
|
||||
start: 2,
|
||||
end: 3,
|
||||
mediaStart: 0,
|
||||
layer: 0,
|
||||
volume: 1,
|
||||
type: "audio",
|
||||
},
|
||||
],
|
||||
projectDir,
|
||||
workDir,
|
||||
outputPath,
|
||||
4,
|
||||
);
|
||||
|
||||
expect(result.success).toBe(true);
|
||||
expect(firstAudibleSeconds(outputPath)).toBeCloseTo(2, 2);
|
||||
});
|
||||
});
|
||||
expect(result.success).toBe(true);
|
||||
expect(firstAudibleSeconds(outputPath)).toBeCloseTo(2, 2);
|
||||
});
|
||||
},
|
||||
60_000,
|
||||
);
|
||||
|
||||
Reference in New Issue
Block a user