video2document/services/modules/audioSnippets/extract-speaker-snippets.js

const ffmpeg = require("fluent-ffmpeg");
const ffmpegPath = require("ffmpeg-static");

ffmpeg.setFfmpegPath(ffmpegPath);

module.exports = {
    name: "extract-speaker-snippets",
    type: "audio",
    displayname: "Extract Speaker Snippets",

    async function(parameter) {
        return new Promise(async (resolve, reject) => {

            let output = {}

            console.log("Extract Speaker Snippets\n");

            // Pfade
            const AUDIO_PATH = parameter.audioPath; // Gesamt-Audio
            const JSON_PATH = parameter.jsonPath; // json summary
            const OUTPUT_DIR = path.join(__dirname, "/../../../storage/audio/speakerSnippets");


            if (!AUDIO_PATH || !JSON_PATH) {
                console.error("no audioPath or jsonPath available");
                return;
            }

            // Output-Ordner
            if (!fs.existsSync(OUTPUT_DIR)) {
                fs.mkdirSync(OUTPUT_DIR, { recursive: true });
            }

            // JSON laden
            let entries;
                try {
                    entries = JSON.parse(fs.readFileSync(JSON_PATH, "utf8"));
                } catch (err) {
                    console.error("JSON reading failed", err);
                    return;
                }

                if (!Array.isArray(entries)) {
                    console.error("JSON is not an Array");
                    return;
                }

            // Pro Speaker genau EINEN Satz merken
            const speakerMap = {};

            for (const item of entries) {
                if (!speakerMap[item.speaker]) {
                    speakerMap[item.speaker] = item;
                }
            }

            // FFmpeg pro Speaker ausführen (sequenziell)
            for (const speaker of Object.keys(speakerMap)) {
                const data = speakerMap[speaker];

                // ms → Sekunden
                const startSec = data.start / 1000;
                const durationSec = (data.end - data.start) / 1000;

                if (durationSec <= 0) {
                    console.log(`invalid times for Speaker ${speaker}`);
                    continue;
                }

                const outFile = path.join(OUTPUT_DIR, `speaker_${speaker}.wav`);

                await new Promise((res, rej) => {
                    ffmpeg(AUDIO_PATH)
                        .setStartTime(startSec)
                        .setDuration(durationSec)
                        .output(outFile)
                        .on("end", () => {
                            output[`speaker${speaker}`] = {src: outFile, name: `speaker${speaker}`}
                            console.log(`Snippet erstellt: speaker_${speaker}.wav`);
                            res();
                        })
                        .on("error", (err) => {
                            console.error(`FFmpeg Fehler (${speaker})`, err.message);
                            rej();
                        })
                        .run();
                });

            }
            resolve(output)
            console.log("\nAlle Speaker-Snippets erstellt\n");
        })
    }
};