mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-09-04 07:19:52 +00:00
fix(hyperframes-media): fall back to ffmpeg when ffprobe is missing (#1877)
* fix(hyperframes-media): fall back to ffmpeg when ffprobe is missing ffprobeDuration() returned NaN whenever the ffprobe spawn failed for any reason, conflating "ffprobe binary not installed" with "file is corrupt". Some ffmpeg-only distributions (common in curated Windows installs) ship ffmpeg.exe without ffprobe.exe, so every TTS line hit the missing-binary case and audio.mjs read the NaN as a bad WAV, silently dropping an already successfully synthesized line. Now falls back to parsing ffmpeg's own `Duration:` stderr banner when ffprobe specifically ENOENTs, and only returns NaN when the file itself can't be probed by either tool. * fix(hyperframes-media): update skills manifest for ffprobe fallback
This commit is contained in:
@@ -75,12 +75,35 @@ export function withWordIds(words) {
|
||||
return (words ?? []).map((w, i) => ({ id: `w${i}`, text: w.text, start: w.start, end: w.end }));
|
||||
}
|
||||
|
||||
// `ffmpeg -i <file>` prints a `Duration: HH:MM:SS.ms` line to stderr even
|
||||
// though it exits non-zero with no output requested. Parsing pulled out as
|
||||
// a pure function so the ENOENT fallback below can be tested without
|
||||
// depending on whether ffprobe/ffmpeg are actually installed on the
|
||||
// machine running the tests.
|
||||
export function parseFfmpegDurationBanner(stderrText) {
|
||||
const match = /Duration:\s*(\d+):(\d+):(\d+(?:\.\d+)?)/.exec(stderrText ?? "");
|
||||
if (!match) return NaN;
|
||||
const [, hours, minutes, seconds] = match;
|
||||
return Number(hours) * 3600 + Number(minutes) * 60 + Number(seconds);
|
||||
}
|
||||
|
||||
// Some "essentials"-style ffmpeg distributions (common on Windows) ship
|
||||
// ffmpeg.exe without ffprobe.exe. ffprobeDuration's caller (audio.mjs)
|
||||
// otherwise reads a spurious NaN as "the WAV file is corrupt" and drops an
|
||||
// already-successfully-synthesized TTS line, rather than "the tool for
|
||||
// measuring it is missing".
|
||||
function ffmpegDurationFallback(absPath) {
|
||||
const r = spawnSync("ffmpeg", ["-i", absPath], { encoding: "utf8" });
|
||||
return parseFfmpegDurationBanner(r.stderr);
|
||||
}
|
||||
|
||||
export function ffprobeDuration(absPath) {
|
||||
const r = spawnSync(
|
||||
"ffprobe",
|
||||
["-v", "error", "-show_entries", "format=duration", "-of", "default=nw=1:nk=1", absPath],
|
||||
{ encoding: "utf8" },
|
||||
);
|
||||
if (r.error?.code === "ENOENT") return ffmpegDurationFallback(absPath);
|
||||
if (r.status !== 0) return NaN;
|
||||
return parseFloat(String(r.stdout).trim());
|
||||
}
|
||||
|
||||
@@ -0,0 +1,66 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { mkdtempSync, writeFileSync, chmodSync, rmSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
import { tmpdir } from "node:os";
|
||||
import { parseFfmpegDurationBanner, ffprobeDuration } from "./tts.mjs";
|
||||
|
||||
test("parseFfmpegDurationBanner reads ffmpeg's stderr Duration line", () => {
|
||||
const stderr = [
|
||||
"ffmpeg version 6.0",
|
||||
"Input #0, wav, from 'a.wav':",
|
||||
" Duration: 00:00:03.42, bitrate: 705 kb/s",
|
||||
"At least one output file must be specified",
|
||||
].join("\n");
|
||||
assert.equal(parseFfmpegDurationBanner(stderr), 3.42);
|
||||
});
|
||||
|
||||
test("parseFfmpegDurationBanner handles an hours component", () => {
|
||||
const stderr = " Duration: 01:02:03.50, start: 0.000000, bitrate: 128 kb/s";
|
||||
assert.equal(parseFfmpegDurationBanner(stderr), 3723.5);
|
||||
});
|
||||
|
||||
test("parseFfmpegDurationBanner returns NaN when there is no Duration line", () => {
|
||||
assert.ok(Number.isNaN(parseFfmpegDurationBanner("ffmpeg: command not found")));
|
||||
assert.ok(Number.isNaN(parseFfmpegDurationBanner("")));
|
||||
assert.ok(Number.isNaN(parseFfmpegDurationBanner(undefined)));
|
||||
});
|
||||
|
||||
// Regression for the actual bug: ffprobeDuration used to collapse "ffprobe
|
||||
// binary is missing" (ENOENT — the "essentials"-style Windows ffmpeg build
|
||||
// with no ffprobe.exe) and "file is genuinely unreadable" into the same NaN,
|
||||
// giving audio.mjs no way to tell "measure differently" from "give up".
|
||||
//
|
||||
// Builds an isolated PATH containing only a fake `ffmpeg` stub (no `ffprobe`
|
||||
// at all) so ffprobeDuration's spawnSync("ffprobe", ...) call ENOENTs for
|
||||
// real, then verifies it recovers the duration via the ffmpeg fallback
|
||||
// instead of returning NaN.
|
||||
test("ffprobeDuration falls back to ffmpeg when the ffprobe binary itself is missing", () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "tts-ffprobe-fallback-"));
|
||||
const fakeFfmpeg = join(dir, "ffmpeg");
|
||||
writeFileSync(
|
||||
fakeFfmpeg,
|
||||
"#!/bin/sh\necho 'Duration: 00:00:02.50, start: 0.000000, bitrate: 128 kb/s' 1>&2\nexit 1\n",
|
||||
);
|
||||
chmodSync(fakeFfmpeg, 0o755);
|
||||
const originalPath = process.env.PATH;
|
||||
try {
|
||||
process.env.PATH = dir; // only the fake ffmpeg resolves; no real ffprobe on this PATH
|
||||
assert.equal(ffprobeDuration("/does/not/matter.wav"), 2.5);
|
||||
} finally {
|
||||
process.env.PATH = originalPath;
|
||||
rmSync(dir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test("ffprobeDuration returns NaN when neither ffprobe nor ffmpeg resolve", () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), "tts-no-binaries-"));
|
||||
const originalPath = process.env.PATH;
|
||||
try {
|
||||
process.env.PATH = dir; // empty directory — nothing resolves
|
||||
assert.ok(Number.isNaN(ffprobeDuration("/does/not/matter.wav")));
|
||||
} finally {
|
||||
process.env.PATH = originalPath;
|
||||
rmSync(dir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
Reference in New Issue
Block a user