added json to send to frontend for the speaker naming functionality

removed the need to send the transcription module defined audio output format to the frontend, and handle it on the backend instead
removed a debug console output
2026-06-15 18:01:52 +02:00 · 2025-12-05 17:09:45 +01:00 · 2025-12-05 16:45:39 +01:00 · 2025-12-05 15:58:45 +01:00 · 2025-12-05 15:58:17 +01:00 · 2025-11-26 21:57:51 +01:00
14 changed files with 13002 additions and 51 deletions
@@ -21,7 +21,9 @@
    <select name="transkript_type" id="transkript_type">
    </select>
    <select name="output_type" id="output_type">
-      <option value="mp4">mp4</option>
+      <option value="flac">flac</option>
+      <option value="mp3">mp3</option>
+      <option value="wav">wav</option>
    </select>
    <select name="language_option" id="language_option">
    </select>
@@ -12,7 +12,7 @@ function checkBoxes() {
      }
    });

-    if(isChecked){
+    if (isChecked) {
      //Code to submit the video
      var selectedCheckboxes = {};
      checkboxes.forEach(function(checkbox){
@@ -59,6 +59,8 @@ function checkBoxes() {
      }else{
        alert('The given file is not compatible. These are the available types: [".mp4", ".mov", ".avi", ".mkv"].');
      }
+
+
    } else {
      //language only english at the moment
      alert('Please select at least one document type.');
@@ -111,11 +113,11 @@ function handleFiles(files) {
    console.log("Error in script.js handleFiles function");
    console.log(error);
  }
-  
+
 }

 //function to regulate the progress on the progressbar
-function updateProgressBar(bar, value){
+function updateProgressBar(bar, value) {
  try {
    value = Math.round(value);
    bar.querySelector(".progress_fill").style.width = `${value}%`;
@@ -35,6 +35,8 @@ console.log("-------------------------------------------------------------------



+
+
 // --------------------------------------------------------- CLI COMMANDS --------------------------------------------------------- //

 const rl = readline.createInterface({
@@ -127,7 +129,7 @@ electron.ipcMain.handle('get-module-names', async () => {
 electron.ipcMain.on("file_submit", async (event, args) => {
    try {
        let curstep = 0
-        let totalsteps = 2 + args.document.styles.length
+        let totalsteps = 3 + args.document.styles.length

        if(args.document.styles.length == 0)
            throw new Error("At least one Document Style needed");
@@ -137,9 +139,10 @@ electron.ipcMain.on("file_submit", async (event, args) => {
        let audiopath = ""
        let transcriptpath = ""

+        console.log("\n\n Running the Video to Audio Extractor");
        // This code handles the Video to Audio extraction module call
-        await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: args.video.outputType}).then(resp => {
-            // console.log(resp);
+        await mapFunctions.get("module-handler").function(args.video.module, {inputVideoPath: args.video.inputVideoPath, outputType: mapFunctions.get(args.transcription.module).audioformat}).then(resp => {
+            console.log(resp);
            audiopath = resp
            curstep++
            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
@@ -149,31 +152,65 @@ electron.ipcMain.on("file_submit", async (event, args) => {
        })


+        console.log("\n\n Running the Audio to Transcription module");
        // TODO implement transcription module
-        // // This code handles the Audio to Text transcription module call
-        // await mapFunctions.get("module-handler").function(args.transcription.module, audiopath).then(resp => {
-        //     console.log(resp);
-        //     transcriptpath = resp
-        //     curstep++
-        //     mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
-        // }).catch(err => {
-        //     mainWindow.webContents.send("error", err)
-        //     return
-        // })
+        // This code handles the Audio to Text transcription module call
+        await mapFunctions.get("module-handler").function(args.transcription.module, audiopath).then(resp => {
+            console.log(resp);
+            transcriptpath = resp
+            curstep++
+            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
+        }).catch(err => {
+            mainWindow.webContents.send("error", err)
+            return
+        })

+
+        console.log("\n\n Running the Transcription Summarizer module");
+        // This code summarises the transcript, so that it can be used by an llm
+        // await mapFunctions.get("summarize-transcription").function('A:\\programing\\@projects\\video2document\\storage\\transcripts\\IMG_2978.json').then(resp => {
+        await mapFunctions.get("summarize-transcription2").function(transcriptpath).then(resp => {
+            console.log(resp);
+            transcriptpath = resp
+            curstep++
+            mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
+        }).catch(err => {
+            mainWindow.webContents.send("error", err)
+            return
+        })
+
+        console.log("\n\n Running the LLM module");
        // TODO implement documentation module
-        // // This code handles the Text to Document processing module call
-        // for (let i = 0; i < args.document.styles.length; i++) {
-        //     await mapFunctions.get("module-handler").function(args.document.module, {prompt: args.document.styles[i].prompt, transcript: transcriptpath}).then(resp => {
-        //         console.log(resp);
-        //         transcriptpath = resp
-        //         curstep++
-        //         mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
-        //     }).catch(err => {
-        //         mainWindow.webContents.send("error", err)
-        //         return
-        //     })
-        // }
+        // This code handles the Text to Document processing module call
+        for (let i = 0; i < args.document.styles.length; i++) {
+            await mapFunctions.get("module-handler").function(args.document.module, {prompt: args.document.styles[i].prompt, transcript: transcriptpath}).then(resp => {
+                console.log(resp);
+                transcriptpath = resp
+                curstep++
+                mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
+            }).catch(err => {
+                mainWindow.webContents.send("error", err)
+                return
+            })
+        }
+
+        // TODO actually implement this functionality
+        // Module to get the first few lines for each speaker to send to the frontend
+//         await mapFunctions.get("speaker-getter-idfk").function(transcriptpath).then(resp => {
+//             console.log(resp);
+//             transcriptpath = resp
+//             curstep++
+//             mainWindow.webContents.send("progress", {curstep:curstep, totalsteps:totalsteps})
+
+// // {
+// // speakerA: {source: "Pfad zur Audio File"},
+// // speakerB:.....
+// // }
+            mainWindow.webContents.send("speakers", {speakerA:"pfad1", speakerB:"pfad2"})
+//         }).catch(err => {
+//             mainWindow.webContents.send("error", err)
+//             return
+//         })


    } catch (error) {
@@ -213,4 +250,4 @@ let q1 = {
        {name:"abc", displayname:"ABC"},
        {name:"qeg", displayname:"aqghegahu"}
    ]
-}
+}
@@ -11,6 +11,7 @@
      "dependencies": {
        "@google/genai": "^1.30.0",
        "@types/axios": "^0.9.36",
+        "axios": "^1.13.2",
        "cli-progress": "^3.12.0",
        "dotenv": "^17.2.3",
        "electron": "^39.1.1",
@@ -401,6 +402,21 @@
      "resolved": "https://registry.npmjs.org/async/-/async-0.2.10.tgz",
      "integrity": "sha512-eAkdoKxU6/LkKDBzLpT+t6Ff5EtfSF4wx1WfJiPEEV7WNLnDaRXk0oVysiEPm262roaachGexwUv94WhSgN5TQ=="
    },
+    "node_modules/asynckit": {
+      "version": "0.4.0",
+      "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
+      "integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q=="
+    },
+    "node_modules/axios": {
+      "version": "1.13.2",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.13.2.tgz",
+      "integrity": "sha512-VPk9ebNqPcy5lRGuSlKx752IlDatOjT9paPlm8A7yOuW2Fbvp4X3JznJtT4f0GzGLLiWE9W8onz51SqLYwzGaA==",
+      "dependencies": {
+        "follow-redirects": "^1.15.6",
+        "form-data": "^4.0.4",
+        "proxy-from-env": "^1.1.0"
+      }
+    },
    "node_modules/balanced-match": {
      "version": "1.0.2",
      "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
@@ -591,6 +607,17 @@
      "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz",
      "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="
    },
+    "node_modules/combined-stream": {
+      "version": "1.0.8",
+      "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz",
+      "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==",
+      "dependencies": {
+        "delayed-stream": "~1.0.0"
+      },
+      "engines": {
+        "node": ">= 0.8"
+      }
+    },
    "node_modules/concat-stream": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/concat-stream/-/concat-stream-2.0.0.tgz",
@@ -767,6 +794,14 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/delayed-stream": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
+      "integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
+      "engines": {
+        "node": ">=0.4.0"
+      }
+    },
    "node_modules/depd": {
      "version": "2.0.0",
      "resolved": "https://registry.npmjs.org/depd/-/depd-2.0.0.tgz",
@@ -795,7 +830,6 @@
      "version": "17.2.3",
      "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
      "integrity": "sha512-JVUnt+DUIzu87TABbhPmNfVdBDt18BLOWjMUFJMSi/Qqg7NTYtabbvSNJGOJ7afbRuv9D/lngizHtP7QyLQ+9w==",
-      "license": "BSD-2-Clause",
      "engines": {
        "node": ">=12"
      },
@@ -922,6 +956,20 @@
        "node": ">= 0.4"
      }
    },
+    "node_modules/es-set-tostringtag": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
+      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "get-intrinsic": "^1.2.6",
+        "has-tostringtag": "^1.0.2",
+        "hasown": "^2.0.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
    "node_modules/es6-error": {
      "version": "4.1.1",
      "resolved": "https://registry.npmjs.org/es6-error/-/es6-error-4.1.1.tgz",
@@ -1093,6 +1141,25 @@
        "node": ">=18"
      }
    },
+    "node_modules/follow-redirects": {
+      "version": "1.15.11",
+      "resolved": "https://registry.npmjs.org/follow-redirects/-/follow-redirects-1.15.11.tgz",
+      "integrity": "sha512-deG2P0JfjrTxl50XGCDyfI97ZGVCxIpfKYmfyrQ54n5FO/0gfIES8C/Psl6kWVDolizcaaxZJnTS0QSMxvnsBQ==",
+      "funding": [
+        {
+          "type": "individual",
+          "url": "https://github.com/sponsors/RubenVerborgh"
+        }
+      ],
+      "engines": {
+        "node": ">=4.0"
+      },
+      "peerDependenciesMeta": {
+        "debug": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/foreground-child": {
      "version": "3.3.1",
      "resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.1.tgz",
@@ -1108,6 +1175,40 @@
        "url": "https://github.com/sponsors/isaacs"
      }
    },
+    "node_modules/form-data": {
+      "version": "4.0.5",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.5.tgz",
+      "integrity": "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==",
+      "dependencies": {
+        "asynckit": "^0.4.0",
+        "combined-stream": "^1.0.8",
+        "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
+        "mime-types": "^2.1.12"
+      },
+      "engines": {
+        "node": ">= 6"
+      }
+    },
+    "node_modules/form-data/node_modules/mime-db": {
+      "version": "1.52.0",
+      "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.52.0.tgz",
+      "integrity": "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==",
+      "engines": {
+        "node": ">= 0.6"
+      }
+    },
+    "node_modules/form-data/node_modules/mime-types": {
+      "version": "2.1.35",
+      "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.35.tgz",
+      "integrity": "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==",
+      "dependencies": {
+        "mime-db": "1.52.0"
+      },
+      "engines": {
+        "node": ">= 0.6"
+      }
+    },
    "node_modules/formdata-polyfill": {
      "version": "4.0.10",
      "resolved": "https://registry.npmjs.org/formdata-polyfill/-/formdata-polyfill-4.0.10.tgz",
@@ -1416,6 +1517,20 @@
        "url": "https://github.com/sponsors/ljharb"
      }
    },
+    "node_modules/has-tostringtag": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
+      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
+      "dependencies": {
+        "has-symbols": "^1.0.3"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
    "node_modules/hasown": {
      "version": "2.0.2",
      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
@@ -1900,6 +2015,11 @@
        "node": ">= 0.10"
      }
    },
+    "node_modules/proxy-from-env": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/proxy-from-env/-/proxy-from-env-1.1.0.tgz",
+      "integrity": "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="
+    },
    "node_modules/pump": {
      "version": "3.0.3",
      "resolved": "https://registry.npmjs.org/pump/-/pump-3.0.3.tgz",
@@ -2,6 +2,7 @@
  "dependencies": {
    "@google/genai": "^1.30.0",
    "@types/axios": "^0.9.36",
+    "axios": "^1.13.2",
    "cli-progress": "^3.12.0",
    "dotenv": "^17.2.3",
    "electron": "^39.1.1",
@@ -16,4 +16,8 @@ cliProgress = require('cli-progress');
 // { app, BrowserWindow, ipcMain, dialog } = require('electron');

 electron = require('electron');
-genai    = require("@google/genai"); 
+genai    = require("@google/genai");
+
+axios = require("axios")
+
+console.log(require('dotenv').config({path: __dirname + '/.env'}));
@@ -0,0 +1,148 @@
+
+// Prepare output directory (always storage/transcriptionSummaries under project root)
+const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
+if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+}
+
+//Speaker, ALL-Sentences, Start, End
+
+module.exports = {
+    name: "summarize-transcription", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
+    type: "summarizer", // value used to differentiate each module to order them in the UI
+    displayname: "Summarizer",  // The displayname used within the UI
+    async function(args) {
+        return new Promise(async (resolve, reject) => {
+            let inputJson = args.json;
+
+            //JSON Path
+            if (args.jsonPath) {
+                try {
+                    const raw = fs.readFileSync(args.jsonPath, "utf-8");
+                    inputJson = JSON.parse(raw);
+                } catch (e) {
+                    console.error("Failed to load JSON from file:", e);
+                    return { error: "Could not read JSON from file path." };
+                }
+            }
+            // JSON parsen
+            if (typeof args === "string") {
+                try {
+                    await new Promise((res) => {
+                        fs.readFile(args, 'utf8', function (err, data) {
+                            if (err) throw err;
+                            inputJson = JSON.parse(data);
+                            res()
+                        });
+                    })
+                } catch (e) {
+                    console.log("Invalid JSON in summarize-transcription");
+                    console.log(e)
+                    return { error: "Invalid JSON" };
+                }
+            }
+
+            const words = inputJson.words;
+            if (!Array.isArray(words)) {
+                return { error: "No words Array found" };
+            }
+
+            const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
+            const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
+
+            const result = [];
+            let currentSentence = "";
+            let currentSpeaker = null;
+            let startTime = null;
+            let endTime = null;
+
+            for (const w of words) {
+                if (!currentSpeaker) currentSpeaker = w.speaker;
+                if (startTime === null) startTime = w.start;
+                endTime = w.end;
+        
+                //speaker changing
+                if (currentSpeaker !== w.speaker && currentSentence) { 
+                    const lastEntry = result[result.length - 1];
+                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
+                        lastEntry.sentence += " " + currentSentence;
+                        lastEntry.end = endTime;
+                    } else {
+                        result.push({
+                            speaker: currentSpeaker,
+                            sentence: currentSentence,
+                            start: startTime,
+                            end: endTime
+                        });
+                    }
+                    currentSentence = "";
+                    startTime = w.start;
+                }
+                currentSpeaker = w.speaker;
+                currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
+                const lastWord = w.text.trim();
+                const lastChar = lastWord.slice(-1);
+                const isAbbreviation = ABBREVIATIONS.has(lastWord);
+
+                //sentence ending
+                if (ENDINGS.includes(lastChar) && !isAbbreviation) {
+                    const lastEntry = result[result.length - 1];
+                    if (lastEntry && lastEntry.speaker === currentSpeaker) {
+                        lastEntry.sentence += " " + currentSentence;
+                        lastEntry.end = endTime;
+                    } else {
+                        result.push({
+                            speaker: currentSpeaker,
+                            sentence: currentSentence,
+                            start: startTime,
+                            end: endTime
+                        });
+                    }
+                    currentSentence = "";
+                    startTime = null;
+                    endTime = null;
+                    currentSpeaker = null;
+                }
+            }
+
+            // safe last sentence 
+            if (currentSentence) {
+                const lastEntry = result[result.length - 1];
+                if (lastEntry && lastEntry.speaker === currentSpeaker) {
+                    lastEntry.sentence += " " + currentSentence;
+                    lastEntry.end = endTime;
+                } else {
+                    result.push({
+                        speaker: currentSpeaker,
+                        sentence: currentSentence,
+                        start: startTime,
+                        end: endTime
+                    });
+                }
+            }
+
+            // Output as Text
+            const output = result.map(r => 
+                `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
+            );
+
+            // Output on cosole
+            //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
+
+            try {
+                const jsonPath = path.join(outputDir, "transcription_result.json");
+                fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
+
+                const txtPath = path.join(outputDir, "transcription_result.txt");
+                fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
+
+                console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
+
+                resolve(jsonPath);
+            } catch (err) {
+                console.error("Error saving Summary:", err);
+                reject(err);
+            }
+        })
+    }
+}
@@ -0,0 +1,143 @@
+
+// Prepare output directory (always storage/transcriptionSummaries under project root)
+const outputDir = `${__dirname}/../../../storage/transcriptionSummaries`;
+if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+}
+
+function getSessionId(inputPath) {
+  try {
+    const parsed = new URL(inputPath);
+    const base = path.basename(parsed.pathname);
+    return base.replace(/\.[^.]+$/, '');
+  } catch {
+    return path.basename(inputPath, path.extname(inputPath));
+  }
+}
+
+//Speaker, Sentence, Start, End
+
+module.exports = {
+    name: "summarize-transcription2", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
+    type: "summarizer", // value used to differentiate each module to order them in the UI
+    displayname: "Summarizer",  // The displayname used within the UI
+    async function(args) {
+        return new Promise(async (resolve, reject) => {
+            let inputJson = args.json;
+
+            //JSON Path
+            if (args.jsonPath) {
+                try {
+                    const raw = fs.readFileSync(args.jsonPath, "utf-8");
+                    inputJson = JSON.parse(raw);
+                } catch (e) {
+                    console.error("Failed to load JSON from file:", e);
+                    return { error: "Could not read JSON from file path." };
+                }
+            }
+            // JSON parsen
+                if (typeof args === "string") {
+                    try {
+                        await new Promise((res) => {
+                            fs.readFile(args, 'utf8', function (err, data) {
+                                if (err) throw err;
+                                inputJson = JSON.parse(data);
+                                res()
+                            });
+                        })
+                    } catch (e) {
+                        console.log("Invalid JSON in summarize-transcription");
+                        console.log(e)
+                        return { error: "Invalid JSON" };
+                    }
+                }
+
+            const words = inputJson.words;
+            if (!Array.isArray(words)) {
+                return { error: "No words Array found" };
+            }
+
+            const ENDINGS = [".", "!", "?"]; // '...' auch als Satzende ?
+            const ABBREVIATIONS = new Set(["z.B.", "bzw.", "u.a.", "Dr.", "Mr.", "Mrs.", "Prof.", "etc."]); //TODO weitere Ergaenzen
+
+            const result = [];
+            let currentSentence = "";
+            let currentSpeaker = null;
+            let startTime = null;
+            let endTime = null;
+
+            for (const w of words) {
+                if (!currentSpeaker) currentSpeaker = w.speaker;
+                if (startTime === null) startTime = w.start;
+                endTime = w.end;
+        
+                //speaker changing
+                if (currentSpeaker !== w.speaker && currentSentence) {
+                    result.push({
+                        speaker: currentSpeaker,
+                        sentence: currentSentence,
+                        start: startTime,
+                        end: endTime
+                    });
+                    currentSentence = "";
+                    startTime = w.start;
+                }
+                currentSpeaker = w.speaker;
+                currentSentence += (currentSentence ? " " : "") + w.text; //sentence beginning or not
+                const lastWord = w.text.trim();
+                const lastChar = lastWord.slice(-1);
+                const isAbbreviation = ABBREVIATIONS.has(lastWord);
+
+                //sentence ending
+                if (ENDINGS.includes(lastChar) && !isAbbreviation) {
+                    result.push({
+                        speaker: currentSpeaker,
+                        sentence: currentSentence,
+                        start: startTime,
+                        end: endTime
+                    });
+                    currentSentence = "";
+                    startTime = null;
+                    endTime = null;
+                    currentSpeaker = null;
+                }
+            }
+
+            // safe last sentence 
+            if (currentSentence) {
+                result.push({
+                    speaker: currentSpeaker,
+                    sentence: currentSentence,
+                    start: startTime,
+                    end: endTime
+                });
+            }
+
+
+            // Output as Text
+            const output = result.map(r => 
+                `Sprecher ${r.speaker} [${r.start.toFixed(2)} - ${r.end.toFixed(2)}]: ${r.sentence}`
+            );
+
+            // Output on cosole
+            //console.log("\n------------\nMerged Transcription Result:\n", output, "\n------------\n");
+
+            try {
+
+                let filename = getSessionId(args);
+
+                const jsonPath = path.join(outputDir, `${filename}-${new Date().getTime()}.json`);
+                fs.writeFileSync(jsonPath, JSON.stringify(result, null, 2), "utf-8");
+
+                const txtPath = path.join(outputDir, `${filename}-${new Date().getTime()}.txt`);
+                fs.writeFileSync(txtPath, output.join("\n"), "utf-8");
+
+                console.log(`Summary successfully saved:\n- ${jsonPath}\n- ${txtPath}`);
+                resolve(jsonPath);
+            } catch (err) {
+                console.error("Error saving Summary:", err);
+                reject(err);
+            }
+        })
+    }
+}
@@ -4,9 +4,10 @@ if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true }); // Create output directory if it doesn't exist
 }

-const ai = new genai.GoogleGenAI({ 
-    apiKey: process.env.GOOGLE_API_KEY // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
-});
+// Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+
+const GEMINI_API_KEY = process.env.GOOGLE_API_KEY; // Ensure Google API key is set in environment variables: export GOOGLE_API_KEY="your_api_key_here"
+const GEMINI_URL = "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent"; //URL for the REST call, used model and action

 module.exports = {
    name: "llm-gemini",
@@ -31,19 +32,39 @@ module.exports = {

    createDocumentFromTranscript: async function(transcriptPath, documentTypePath, language = "en") { // default language is English
        try {
-            const transcript = await fs.promises.readFile(transcriptPath, "utf-8");
-            const documentType = await fs.promises.readFile(documentTypePath, "utf-8");
+            const transcript = await fs.promises.readFile(transcriptPath, "utf-8"); //read transcript file from Path
+            const documentType = await fs.promises.readFile(documentTypePath, "utf-8"); //read document type from Path
+            const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`; //combine doc type, language and transcript - Change prompt here if needed

-            const promptText = `${documentType}, in language ${language}, transcript:\n\n${transcript}`;
-
-            const response = await ai.models.generateContent({
-                model: "gemini-2.5-flash", // Specify the Gemini model to use
-                contents: promptText // Input prompt for content generation
+            // --- REST CALL ---
+            const response = await fetch(`${GEMINI_URL}?key=${GEMINI_API_KEY}`, { //safe model response in variable
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/json"
+                },
+                body: JSON.stringify({
+                    contents: [
+                        {
+                            parts: [
+                                { text: promptText } // Input prompt for content generation
+                            ]
+                        }
+                    ]
+                })
            });

-            const output = response.text || ""; // Get generated text from response or default to empty string (if null)
+            if (!response.ok) { //ok is true when a responce was successfull
+                const text = await response.text();
+                throw new Error(`Gemini API error (${response.status}): ${text}`);
+            }

-            const outPath = path.join(outputDir, "test.md"); // Output file path & name TO BE DONE to make dynamic out of input transcript name
+            const data = await response.json();
+
+            // Get generated text from response or default to empty string (if null)
+            const output = data?.candidates?.[0]?.content?.parts?.[0]?.text || "";
+            let inputTranscriptName = path.basename(transcriptPath, path.extname(transcriptPath)); // Name for the output file 
+            console.log(inputTranscriptName);
+            const outPath = path.join(outputDir, `${inputTranscriptName}.md`); // Output file path & name to make naming dynamic. Pulled from input transcript name
            fs.writeFileSync(outPath, output, "utf8"); // Write output to file

            console.log("Generated document written to:", outPath);
@@ -1,8 +1,124 @@
-module.exports = {
-    name:"assembly", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
-    type:"transcription", // value used to differentiate each module to order them in the UI
-    displayname:"Assembly", // The displayname used within the UI
-    async function(parameter){
-        // TODO add code to actually process the audio file
+const API_KEY = process.env.ASSEMBLYAI_API_KEY;
+const BASE_URL = 'https://api.assemblyai.com/v2';
+
+//---------------------------------------------------Upload audio---------------------------------------------------
+
+async function uploadAudio(audioPath) {
+  const audioData = fs.readFileSync(audioPath);
+
+  const response = await axios.post(`${BASE_URL}/upload`, audioData, {
+    headers: {
+      authorization: API_KEY,
+      'content-type': 'application/octet-stream'
    }
-}
+  });
+
+  return response.data.upload_url;
+}
+
+////---------------------------------------------------Extract session id---------------------------------------------------
+
+function getSessionId(inputPath) {
+  try {
+    const parsed = new URL(inputPath);
+    const base = path.basename(parsed.pathname);
+    return base.replace(/\.[^.]+$/, '');
+  } catch {
+    return path.basename(inputPath, path.extname(inputPath));
+  }
+}
+
+//---------------------------------------------------Create transcript---------------------------------------------------
+
+async function createTranscript(audioUrl) {
+  const response = await axios.post(
+    `${BASE_URL}/transcript`,
+    {
+      audio_url: audioUrl,
+      speaker_labels: true,
+      language_detection: true
+    },
+    {
+      headers: {
+        authorization: API_KEY,
+        'content-type': 'application/json'
+      }
+    }
+  );
+
+  return response.data.id;
+}
+
+//---------------------------------------------------Poll transcript---------------------------------------------------
+
+async function pollTranscript(transcriptId) {
+  while (true) {
+    const response = await axios.get(`${BASE_URL}/transcript/${transcriptId}`, {
+      headers: { authorization: API_KEY }
+    });
+
+    const status = response.data.status;
+
+    if (status === 'completed') return response.data;
+    if (status === 'error') throw new Error(`Transcription failed: ${response.data.error}`);
+
+    await new Promise(res => setTimeout(res, 3000));
+  }
+}
+
+//---------------------------------------------------Save transcript---------------------------------------------------
+
+function saveTranscript(transcript, sessionId) {
+  const outputDir = path.join(__dirname, '../../../storage/transcripts');
+
+  if (!fs.existsSync(outputDir)) {
+    fs.mkdirSync(outputDir, { recursive: true });
+  }
+
+  const outputPath = path.join(outputDir, `${sessionId}.json`);
+  fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
+
+  console.log(`Transcript saved: ${outputPath}`);
+
+  return outputPath;
+}
+
+//---------------------------------------------------Modul---------------------------------------------------
+
+module.exports = {
+  name: 'assembly',
+  type: 'transcription',
+  displayname: 'AssemblyAI',
+  audioformat: "mp3",
+
+  async function(audioFileName) {
+    return new Promise(async (resolve, reject) => {
+      try {
+        // audioFileName ist nur "datei.mp3"
+        const audioPath = audioFileName;
+
+        let audioUrl;
+
+        if (/^https?:\/\//i.test(audioFileName)) {
+          audioUrl = audioFileName;
+        } else {
+          if (!fs.existsSync(audioPath)) {
+            throw new Error(`Audio file not found: ${audioPath}`);
+          }
+          audioUrl = await uploadAudio(audioPath);
+        }
+
+        const transcriptId = await createTranscript(audioUrl);
+        const transcript = await pollTranscript(transcriptId);
+
+        const sessionId = getSessionId(audioFileName);
+        
+        resolve(saveTranscript(transcript, sessionId));
+
+      } catch (error) {
+        console.error('Transcription error:', error.message);
+        reject(error);
+      }
+    })
+  }
+};
@@ -6,6 +6,13 @@ module.exports = {
        // We are now calling the example function from the example folder
        mapFunctions.get("example").function("Startup")

+    //    let transcript = await mapFunctions.get("assembly").function('../../storage/audio/IMG_2978.wav');
+
+    //    let summary = await mapFunctions.get("summarize-transcription").function({jsonPath:'/Users/santa/Proj25/video2document/storage/transcripts/IMG_2978.json'});
+
+
+        
+
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"wav"})
        // mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./b.mp4", outputType:"flac"})
@@ -0,0 +1,18 @@
+require('dotenv').config();
+const path = require('path');
+const assemblyModule = require('../../services/modules/transcription-remote/assembly.js');
+
+// Audio-Datei oder URL aus Kommandozeile, Standard: test.wav
+const audioPath = process.argv[2] || './storage/audio/IMG_2978.wav';
+
+(async () => {
+  try {
+    const transcript = await assemblyModule.run(audioPath);
+
+    console.log('Transcription succesful');
+    console.log('Transcript ID:', transcript?.id);
+    console.log('Speaker labels:', transcript?.utterances?.length || 0);
+  } catch (error) {
+    console.error('Error in Transcription:', error?.message || error);
+  }
+})();
@@ -0,0 +1,12 @@
+const fs = require('fs');
+const transSummarizer = require("../../services/modules/jsonTools/transcriptionSummarizer.js");
+
+// JSON-Datei laden
+const inputJson = JSON.parse(fs.readFileSync("./testFile.json", "utf8"));
+
+// Übergabe an den Summarizer
+transSummarizer.function({
+    json: inputJson
+});
+
+
Author	SHA1	Message	Date
emily	e661aefbe8	added json to send to frontend for the speaker naming functionality	2025-12-05 17:09:45 +01:00
emily	ed94928953	removed the need to send the transcription module defined audio output format to the frontend, and handle it on the backend instead	2025-12-05 16:45:39 +01:00
emily	8adf470f18	removed a debug console output	2025-12-05 15:58:45 +01:00
emily	f858f2edbb	added functionality for transcription tool to tell the frontend what audio format to use	2025-12-05 15:58:17 +01:00
Spanier, Pit	05c04aaef2	Merge branch 'feature/gemini-ai' into 'develop' REST API & Auto Naming See merge request proj-wise2526-video2document/video2document!31	2025-11-26 21:57:51 +01:00
MikeHughes-BIN	84cc94aa34	REST API & Auto Naming	2025-11-26 21:55:19 +01:00
Spanier, Pit	16f319f89f	Merge branch 'feature/implementing-everything' into 'develop' working on implementing everything See merge request proj-wise2526-video2document/video2document!27	2025-11-24 17:25:37 +01:00
santa	9ab98825a2	made it so that the transcript summary file name is not hardcoded anymore	2025-11-24 17:24:08 +01:00
emily	9a0a349813	Switched to transcription summarizer2 due to a better output format	2025-11-24 17:01:49 +01:00
emily	9dfc05e987	Fixed Transcription Summarizer, and now the whole pipeline works (except for LLM, because we need the keys for that)	2025-11-24 16:51:48 +01:00
santa	a5a60635fc	worked on fixing the code	2025-11-24 16:40:12 +01:00
emily	af13907fdc	added console outputs for debugging	2025-11-24 16:14:26 +01:00
emily	812bca8cfb	working on implementing everything Currently getting stuck on the assembly module as assembly ai for some fucking reason blocks me from making any requests This includes making a new user account	2025-11-24 15:35:32 +01:00
emily	34d644d7d7	Merge commit '2f5efee9c7f81cadc22f033f9ba20bb5cbc2d66e' into develop	2025-11-24 14:41:10 +01:00
Spanier, Pit	e73a2a8203	Merge branch 'feature/modular-ipc-system-implementation' into 'develop' Implemented first version of the json object that should be send back to the... See merge request proj-wise2526-video2document/video2document!26	2025-11-24 14:31:32 +01:00
santa	2f5efee9c7	Summarizer und weiters angepasst	2025-11-24 14:27:49 +01:00
santa	465fe8bd41	Summarizer angepasst	2025-11-24 14:25:29 +01:00
Hughes, Mike	0f689e2846	Merge branch 'feature/26-llm-schnittstelle-implementieren-s3-07' into 'develop' Feature/26 llm schnittstelle implementieren s3 07 See merge request proj-wise2526-video2document/video2document!24	2025-11-22 14:38:07 +01:00
santa	b87bfd444d	Test erstellt	2025-11-20 13:27:15 +01:00
santa	97b571b7f9	Einbindung des Summarizer	2025-11-20 11:51:34 +01:00
santa	455147a41b	Summarizer Tool erstellt zur zusammenfassung der vom TranskriptionTool kommenden json	2025-11-20 10:15:11 +01:00
santa	9441699561	if Pruefung fuer Datei Endung gefixt	2025-11-16 14:46:19 +01:00