Compare commits

...

20 Commits

Author SHA1 Message Date
MikeHughes-BIN 79e0c48755 Reduced Number of test paths to avoid redundancy 2025-11-13 17:35:40 +01:00
MikeHughes-BIN 9254ddc57f Changed the Folder Structure for better maintainability 2025-11-13 17:34:22 +01:00
Azeufack Noupeu Willy c021272ca4 merge: Resolve conflicts with develop 2025-11-13 15:22:33 +01:00
Azeufack Noupeu Willy e7e97a7f60 feat(S2-02b): Implement AssemblyAI external transcription with speaker diarization
- Add assembly.ts module for REST API transcription via AssemblyAI
- Implement 5-step pipeline: upload → create job → poll status → download → save
- Enable speaker_labels for diarization (Speaker A, B, C...)
- Add millisecond-precision timestamps for each utterance
- Store JSON transcripts in storage/transcripts/{session_id}.json
- Add axios, dotenv dependencies
- Add transcribeLatest.ts helper for quick testing

User Story: S2-02b - Externe Transkription per REST API
2025-11-13 13:07:18 +01:00
Spanier, Pit 80392874bb Merge branch 'feature/combination-of-all-the-things' into 'develop'
Fixed an error in checkBoxes function and uploadContainer "drop" listener...

See merge request proj-wise2526-video2document/video2document!15
2025-11-12 20:56:11 +01:00
emily 94f390f28b Implemented audio extractor into IPC call, sooooooo, frontend and backend are now officially linked successfully 2025-11-12 20:28:55 +01:00
emily 73f6fa7524 fixed the code so that it now returns the actual path of the file 2025-11-12 20:24:45 +01:00
emily 87e3368a9a fixed code 2025-11-12 20:04:48 +01:00
emily 6d9c94c685 removed some debug console outputs 2025-11-12 20:03:09 +01:00
emily fbd5368223 Implemented functionality to have the UI be able to communicate with the backend 2025-11-12 20:00:25 +01:00
emily 449255dda1 Merge commit 'c8cbd4e92a034fa108d06337a3e63d24e529432f' into feature/combination-of-all-the-things 2025-11-12 19:55:50 +01:00
eric.minning c8cbd4e92a Fixed an error in checkBoxes function and uploadContainer "drop" listener regarding file path testing 2025-11-12 18:52:28 +01:00
eric.minning 0f54edb0aa Removed the variables at the start of the script.js file 2025-11-12 18:44:27 +01:00
eric.minning 54f1f6c135 Added the check if a path is selected and the call to the transcript functio. 2025-11-12 18:16:27 +01:00
Verena Schulz a32e7e5744 Checkboxes check (with alert) 2025-11-12 17:39:02 +01:00
Verena Schulz d9e96316c0 Language selection implemented and UI reworked 2025-11-11 18:31:01 +01:00
eric.minning da3a8c7d8c Added try/catch handling and some comments 2025-11-11 16:02:07 +01:00
emily dfe91bb15a Merge commit '3a8963b49d96d0746b64244fa17458d4ae68ec45' into feature/combination-of-all-the-things 2025-11-10 17:01:30 +01:00
emily 92043440fe Combined Frontend with backend, and implemented the extractor function into the module structure 2025-11-10 16:18:57 +01:00
emily bd8ed1bf81 added mp4, flac and wav files to gitignore 2025-11-10 16:12:59 +01:00
25 changed files with 2197 additions and 161 deletions
+5 -1
View File
@@ -964,4 +964,8 @@ app.*.symbols
!/dev/ci/**/Gemfile.lock
#Storage files
storage/
storage/
*.mp4
*.wav
*.flac
Binary file not shown.

After

Width:  |  Height:  |  Size: 2.6 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 18 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 35 KiB

+16 -9
View File
@@ -3,15 +3,22 @@
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Video Upload Drag and Drop + Button</title>
<title id="title">Video to document</title>
<link rel="stylesheet" href="style.css">
</head>
<body>
<div class="mitte" id="mitte">
<h1>Video to document</h1>
<div class="flagsBtns" id="flagsBtns">
<button class="de_Btn" id="de_Btn" onclick="changeLanguage('de')"><img src="flags/germany-flag-png-large.jpg" width="25px" height="20px"/></button>
<button class="eng_Btn" id="eng_Btn" onclick="changeLanguage('en')"><img src="flags/united-kingdom-flag-png-large.jpg" width="25px" height="20px"/></button>
<button class="in_Btn" id="in_Btn" onclick="changeLanguage('in')"><img src="flags/india-flag-png-large.png" width="25px" height="20px"/></button>
</div>
<h1 id="h1">Video to document</h1>
<div class="upload-container" id="uploadContainer">
<p>Drag and drop video file</p>
<p id="p1">Drag and drop video file</p>
<div class="file-name" id="fileName">No video chosen</div>
</div>
@@ -19,19 +26,19 @@
<input type="file" id="videoUpload" accept="video/*">
<div class="checkbox-group">
<label for="checkbox-group">Choose prefered document style:</label>
<label id="checkbox_group" for="checkbox-group">Choose prefered document style:</label>
<div class="checkbox-container">
<input type="checkbox" id="docFormat">
<label for "docFormat">Meeting report</label>
<input type="checkbox" name ="docFormat" id="docFormat">
<label id="label_format" for="docFormat">Meeting report</label>
</div>
<div class="checkbox-container">
<input type="checkbox" id="docFormatCustom">
<label for "docFormatCustom">Summary with timestamps</label>
<input type="checkbox" name="docFormat" id="docFormatSummary">
<label id="label_summary" for="docFormatSummary">Summary with timestamps</label>
</div>
</div>
<button class="submit-btn" id="submitButton">Submit Video</button>
<button class="submit-btn" id="submitButton" onclick="checkBoxes()">Submit</button>
<div class="progressbar">
<div class="progress_fill"></div>
+14 -3
View File
@@ -2,6 +2,17 @@
const { contextBridge, ipcRenderer, webUtils } = require('electron')
contextBridge.exposeInMainWorld("explorer", {
onFileDrop: (file) => webUtils.getPathForFile(file)
})
try {
contextBridge.exposeInMainWorld("explorer", {
onFileDrop: (file) => webUtils.getPathForFile(file)
})
contextBridge.exposeInMainWorld("extractor", {
extract: (file) => ipcRenderer.send("extract", file)
})
contextBridge.exposeInMainWorld("electronAPI", {
getFilePath: (file) => {return webUtils.getPathForFile(file)}
})
} catch (error) {
console.log("Error in preload.js");
}
+27 -18
View File
@@ -1,22 +1,31 @@
const dropzone = document.getElementById("uploadContainer");
dropzone.addEventListener("dragover", (e) =>{
e.stopPropagation();
e.preventDefault();
});
dropzone.addEventListener("drop", (e) => {
e.stopPropagation()
e.preventDefault()
const files = e.dataTransfer.files
const filePath = window.explorer.onFileDrop(files[0])
var holdy = filePath + "";
if(holdy.endsWith(".mp4")){
console.log(filePath)
const files1 = e.dataTransfer.files;
handleFiles(files1);
uploadContainer.addEventListener("dragover", (e) =>{
try {
e.stopPropagation();
e.preventDefault();
} catch (error) {
console.log("Error in renderer.js dragover listener function")
}
});
//listener for when a file get dropped on the drag&drop field
uploadContainer.addEventListener("drop", (e) => {
try {
e.stopPropagation()
e.preventDefault()
const files = e.dataTransfer.files
const filePath = window.explorer.onFileDrop(files[0])
var holdy = filePath + "";
if(holdy.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
console.log(filePath)
const files1 = e.dataTransfer.files;
handleFiles(files1);
}
} catch (error) {
console.log("Error in renderer.js with the listerner for the drop function");
}
})
+103 -25
View File
@@ -1,37 +1,115 @@
const uploadContainer = document.getElementById('uploadContainer');
const fileInput = document.getElementById('videoUpload');
const fileName = document.getElementById('fileName');
const manualBtn = document.getElementById('manualUploadBtn');
const videoPreview = document.getElementById('videoPreview');
manualBtn.addEventListener('click', () => {
fileInput.click();
//listener for the file explorer search
manualUploadBtn.addEventListener('click', () => {
try {
videoUpload.click();
} catch (error) {
console.log("Error in manualBtn EventListener click");
}
});
//function to check if one checkbox is at least klicked
function checkBoxes() {
try {
const checkboxes = document.querySelectorAll('input[name="docFormat"]');
let isChecked = false;
fileInput.addEventListener('change', () => {
handleFiles(fileInput.files);
});
checkboxes.forEach(function(checkbox){
if(checkbox.checked){
isChecked = true;
}
});
if(isChecked){
//Code to submit the video
var pathTest = window.electronAPI.getFilePath(videoUpload.files[0]);
if(pathTest.endsWith(".mp4") || holdy.endsWith(".mov") || holdy.endsWith(".avi") || holdy.endsWith( ".mkv")){
window.extractor.extract({inputVideoPath: pathTest, outputType:"wav"})
}
} else {
//language only english at the moment
alert('Please select at least one document type.');
}
} catch (error) {
console.log(error)
}
// mapFunctions.get("extraction-video-to-audio").function({inputVideoPath:"./a.mp4", outputType:"wav"})
}
function handleFiles(files) {
if (files.length > 0) {
const file = files[0];
if (file.type.startsWith('video/')) {
fileInput.files = files;
fileName.textContent = `Chosen video: ${file.name}`;
//language changing feature
function changeLanguage(language) {
if (language === 'en') {
document.getElementById('title').textContent = 'Video to document';
document.getElementById('h1').textContent = 'Video to document';
document.getElementById('p1').textContent = 'Drag and drop video file';
document.getElementById('fileName').textContent = 'No video chosen';
document.getElementById('manualUploadBtn').textContent = 'Search video';
document.getElementById('checkbox_group').textContent = 'Choose prefered document style:';
document.getElementById('label_format').textContent = 'Meeting report';
document.getElementById('label_summary').textContent = 'Summary with timestamps';
document.getElementById('submitButton').textContent = 'Submit';
} else if (language === 'de') {
document.getElementById('title').textContent = 'Video zu Dokument';
document.getElementById('h1').textContent = 'Video zu Dokument';
document.getElementById('p1').textContent = 'Video per Drag & Drop ablegen';
document.getElementById('fileName').textContent = 'Kein Video ausgewaehlt';
document.getElementById('manualUploadBtn').textContent = 'Video suchen';
document.getElementById('checkbox_group').textContent = 'Bevorzugte Dokumentvarianten:';
document.getElementById('label_format').textContent = 'Meeting Bericht';
document.getElementById('label_summary').textContent = 'Zusammenfassung mit Zeitstempeln';
document.getElementById('submitButton').textContent = 'Absenden';
} else if(language == "in") {
document.getElementById('title').textContent = 'दस्तावेज़ के लिए वीडियो';
document.getElementById('h1').textContent = 'दस्तावेज़ के लिए वीडियो';
document.getElementById('p1').textContent = 'वीडियो फ़ाइल खींचें और छोड़ें';
document.getElementById('fileName').textContent = 'कोई वीडियो नहीं चुना गया';
document.getElementById('manualUploadBtn').textContent = 'वीडियो खोजें';
document.getElementById('checkbox_group').textContent = 'पसंदीदा दस्तावेज़ शैली चुनें:';
document.getElementById('label_format').textContent = 'बैठक रिपोर्ट';
document.getElementById('label_summary').textContent = 'टाइमस्टैम्प के साथ सारांश';
document.getElementById('submitButton').textContent = 'जमा करना';
}
}
//listener for the file explorer search when something got selected
videoUpload.addEventListener('change', () => {
try {
handleFiles(videoUpload.files);
} catch (error) {
console.log("Error in manualBtn EventListener change");
}
});
//function to display the file path in the drop down box
function handleFiles(files) {
try {
if (files.length > 0) {
const file = files[0];
if (file.type.startsWith('video/')) {
videoUpload.files = files;
fileName.textContent = `Chosen video: ${file.name}`;
}
}
} catch (error) {
console.log("Error in script.js handleFiles function");
}
}
//function to regulate the progress on the progressbar
function updateProgressBar(bar, value){
value = Math.round(value);
bar.querySelector(".progress_fill").style.width = `${value}%`;
bar.querySelector(".progress_text").textContent = `${value}%`;
try {
value = Math.round(value);
bar.querySelector(".progress_fill").style.width = `${value}%`;
bar.querySelector(".progress_text").textContent = `${value}%`;
} catch (error) {
console.log("Error in scripts.js updateProgressBar function");
}
}
+19 -4
View File
@@ -5,7 +5,7 @@ body {
justify-content: center;
align-items: center;
height: 100vh;
background-color: #444;
background-color: #555;
gap: 15px;
margin: 0;
}
@@ -75,6 +75,7 @@ gap: 5px;
.checkbox-group {
margin-top: 15px;
margin-bottom: 15px;
display: flex;
flex-direction: column;
gap: 10px;
@@ -92,14 +93,14 @@ gap: 5px;
}
.mitte {
background-color: #eaf0ff;
background-color: #f2f3f4;
display: flex;
flex-direction: column;
align-items: center;
padding: 5% 50px;
margin-top: 20px;
gap: 10px;
border: 2px;
border: 1px;
border-color: black;
border-style: solid;
}
@@ -112,7 +113,7 @@ h1 {
position: relative;
width: 210px;
height: 30px;
background: darkslategray;
background: rgb(42, 46, 78);
border-radius: 5px;
overflow: hidden;
}
@@ -129,4 +130,18 @@ h1 {
top: 50%;
right: 5px;
transform: translateY(-50%);
color: white;
}
.flagsBtns {
display: flex;
justify-content: flex-end;
}
.de_Btn, .eng_Btn, .in_Btn {
padding: 8px 16px;
color: white;
border: none;
border-radius: 8px;
cursor: pointer;
}
+22 -1
View File
@@ -55,4 +55,25 @@ rl.on("line", data =>{
// ----------------------------------------------------------- ELECTRON ----------------------------------------------------------- //
// TODO - Add Electron support to the project
let mainWindow;
function createWindow() {
mainWindow = new electron.BrowserWindow({
width: 800,
height: 600,
webPreferences: {
nodeIntegration: false,
contextIsolation: true,
preload: `${mainDir}/electron/main/preload.js`
}
});
mainWindow.loadFile('./electron/main/index.html');
}
electron.app.whenReady().then(createWindow);
electron.ipcMain.on("extract", (event, args) => {
mapFunctions.get("extraction-video-to-audio").function(args)
})
+1355 -5
View File
File diff suppressed because it is too large Load Diff
+4 -5
View File
@@ -1,10 +1,10 @@
{
"type": "module",
"dependencies": {
"cli-progress": "^3.12.0",
"electron": "^39.1.1",
"express": "^5.1.0",
"ffmpeg-static": "^5.2.0",
"fluent-ffmpeg": "^2.1.3",
"express": "^5.1.0"
"fluent-ffmpeg": "^2.1.3"
},
"devDependencies": {
"@types/cli-progress": "^3.11.6",
@@ -22,6 +22,7 @@
"test": "tests"
},
"scripts": {
"start": "electron main.js",
"test": "echo \"Error: no test specified\" && exit 1"
},
"repository": {
@@ -31,5 +32,3 @@
"author": "",
"license": "ISC"
}
+8
View File
@@ -8,3 +8,11 @@ fs = require("fs")
readline = require("readline")
config = require("./config/config")
ffmpegPath = require('ffmpeg-static');
ffmpeg = require('fluent-ffmpeg');
path = require('path');
cliProgress = require('cli-progress');
// { app, BrowserWindow, ipcMain, dialog } = require('electron');
electron = require('electron');
@@ -0,0 +1,93 @@
// Ensure ffmpeg binary is available
if (!ffmpegPath) {
throw new Error('FFmpeg binary not found!');
}
ffmpeg.setFfmpegPath(ffmpegPath);
// Prepare output directory (always storage/audio under project root)
const outputDir = `${__dirname}/../../../storage/audio`;
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
module.exports = {
name:"extraction-video-to-audio", // Unique name for our function that will later be used to get the function from the map via "mapFunctions.get("example").function()"
type:"extractor", // value used to differentiate each module to order them in the UI
displayname:"Default extractor", // The displayname used within the UI
async function(parameter){
/*
parameter structure:
{
inputVideoPath: String, // Path to the file
outputType: String // Audio file output format
}
*/
let progressBar = new cliProgress.SingleBar({
format: 'Processing |{bar}| {percentage}% | {timemark}',
barCompleteChar: '\u2588',
barIncompleteChar: '\u2591',
hideCursor: true
});
try {
// if (meta.url === `file://${process.argv[1]}`) {
this.extractAudioFromVideo(parameter.inputVideoPath, progressBar, parameter.outputType)
.then(() => console.log('Audio extraction successful.'))
.catch((err) => console.error(err));
// }
} catch (error) {
console.log(parameter.outputType);
}
},
// Derive input and output paths
// const inputVideoPath = process.argv[2];
// console.log(process.argv);
/**
* Extracts audio from a video using ffmpeg.
* - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
* - Shows CLI progress bar
* - Handles errors gracefully (without errors)
*/
extractAudioFromVideo: async function (videoFilePath, progressBar, outputType){
let inputVideoName = path.basename(videoFilePath, path.extname(videoFilePath));
let outputAudioPath = path.join(outputDir, `${inputVideoName}.${outputType}`);
return new Promise((resolve, reject) => {
try {
ffmpeg(videoFilePath)
.outputFormat(outputType)
// .audioCodec('pcm_s16le')
.audioChannels(1)
.audioFrequency(16000)
// .setFfmpegPath("./ffmpeg.exe")
.on('progress', (progress) => {
if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
if (progress.percent) {
progressBar.update(progress.percent, { timemark: progress.timemark });
}
})
.on('end', () => {
progressBar.update(100, { timemark: 'done' });
progressBar.stop();
console.log(`Extraction completed: ${outputAudioPath}`);
resolve();
})
.on('error', (err) => {
progressBar.stop();
console.error(`failed_audio_extraction on type ${outputType}: ${err.message}`);
reject(err);
})
.save(outputAudioPath);
} catch (error) {
console.log();
}
});
}
}
@@ -1,90 +0,0 @@
import ffmpegPath from 'ffmpeg-static';
import ffmpeg from 'fluent-ffmpeg';
import path from 'path';
import fs from 'fs';
import cliProgress from 'cli-progress';
import { fileURLToPath } from 'url';
// Base code reference: https://docs.yemreak.com/arsiv/programming/extract-audio-from-video-with-typescript-and-ffmpeg
// Test command: npx ts-node ./extract.ts /path/to/video.mp4
/**
* Extracts audio from a video file and saves it as WAV.
* @param videoFilePath Path to the input video file.
*/
// Ensure ffmpeg binary is available
if (!ffmpegPath) {
throw new Error('FFmpeg binary not found!');
}
ffmpeg.setFfmpegPath(ffmpegPath);
// Ensure an input video path is provided via CLI
if (process.argv.length < 3) {
console.error('Usage: ts-node ./extract.ts <input-video-path>');
process.exit(1);
}
// Resolve __dirname equivalent in ESM
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
// Prepare output directory (always storage/audio under project root)
const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'audio');
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
// Derive input and output paths
const inputVideoPath = process.argv[2];
const inputVideoName = path.basename(inputVideoPath, path.extname(inputVideoPath));
const outputAudioPath = path.join(outputDir, `${inputVideoName}.wav`);
// Initialize CLI progress bar
const progressBar = new cliProgress.SingleBar({
format: 'Processing |{bar}| {percentage}% | {timemark}',
barCompleteChar: '\u2588',
barIncompleteChar: '\u2591',
hideCursor: true
});
/**
* Extracts audio from a video using ffmpeg.
* - Converts video to WAV (16 kHz, Mono, PCM optional if needed)
* - Shows CLI progress bar
* - Handles errors gracefully (without errors)
*/
export function extractAudioFromVideo(videoFilePath: string): Promise<void> {
return new Promise((resolve, reject) => {
ffmpeg(videoFilePath)
.outputFormat('wav')
.audioCodec('pcm_s16le')
.audioChannels(1)
.audioFrequency(16000)
.on('progress', (progress) => {
if (!progressBar.isActive) progressBar.start(100, 0, { timemark: '00:00:00' });
if (progress.percent) {
progressBar.update(progress.percent, { timemark: progress.timemark });
}
})
.on('end', () => {
progressBar.update(100, { timemark: 'done' });
progressBar.stop();
console.log(`Extraction completed: ${outputAudioPath}`);
resolve();
})
.on('error', (err) => {
progressBar.stop();
console.error(`failed_audio_extraction: ${err.message}`);
reject(err);
})
.save(outputAudioPath);
});
}
// Run extraction if executed directly from CLI
if (import.meta.url === `file://${process.argv[1]}`) {
extractAudioFromVideo(inputVideoPath)
.then(() => console.log('Audio extraction successful.'))
.catch((err) => console.error(err));
}
@@ -0,0 +1,14 @@
import 'dotenv/config';
import assemblyModule from './assembly.ts';
// Test: URL passed as argument OR local file ./storage/audio/test.wav
const audioPath = process.argv[2] || './storage/audio/test.wav';
assemblyModule.run(audioPath)
.then(result => {
console.log('✅ Success!');
console.log('Transcript ID:', result.id);
})
.catch(error => {
console.error('❌ Error:', error?.message || error);
});
@@ -0,0 +1,133 @@
import 'dotenv/config';
import axios from 'axios';
import fs from 'fs';
import path from 'path';
import { fileURLToPath } from 'url';
const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);
const API_KEY = process.env.ASSEMBLYAI_API_KEY;
const BASE_URL = 'https://api.assemblyai.com/v2';
/**
* Uploads audio file to AssemblyAI
*/
async function uploadAudio(audioPath: string): Promise<string> {
const audioData = fs.readFileSync(audioPath);
const response = await axios.post<{ upload_url: string }>(`${BASE_URL}/upload`, audioData, {
headers: {
'authorization': API_KEY,
'content-type': 'application/octet-stream'
}
});
return response.data.upload_url;
}
/**
* Extract a session id (basename without extension) from a local path or a URL
*/
function getSessionId(inputPath: string): string {
try {
const parsed = new URL(inputPath);
const base = path.basename(parsed.pathname);
return base.replace(/\.[^.]+$/, '');
} catch (err) {
// not a URL, treat as local path
return path.basename(inputPath, path.extname(inputPath));
}
}
/**
* Creates transcription job with speaker diarization
*/
async function createTranscript(audioUrl: string): Promise<string> {
const response = await axios.post<{ id: string }>(`${BASE_URL}/transcript`, {
audio_url: audioUrl,
speaker_labels: true,
language_detection: true
}, {
headers: {
'authorization': API_KEY,
'content-type': 'application/json'
}
});
return response.data.id;
}
/**
* Polls transcript status until completed
*/
async function pollTranscript(transcriptId: string): Promise<any> {
while (true) {
const response = await axios.get<any>(`${BASE_URL}/transcript/${transcriptId}`, {
headers: { 'authorization': API_KEY }
});
const status = response.data.status;
if (status === 'completed') {
return response.data;
} else if (status === 'error') {
throw new Error(`Transcription failed: ${response.data.error}`);
}
// Wait 3 seconds before next poll
await new Promise(resolve => setTimeout(resolve, 3000));
}
}
/**
* Saves transcript to storage
*/
function saveTranscript(transcript: any, sessionId: string): void {
const outputDir = path.join(__dirname, '..', '..', '..', 'storage', 'transcripts');
if (!fs.existsSync(outputDir)) {
fs.mkdirSync(outputDir, { recursive: true });
}
const outputPath = path.join(outputDir, `${sessionId}.json`);
fs.writeFileSync(outputPath, JSON.stringify(transcript, null, 2));
console.log(`✅ Transcript saved: ${outputPath}`);
}
export default {
name: "assembly",
type: "transcription",
displayname: "AssemblyAI",
run: async (audioPath: string) => {
try {
// Determine if audioPath is an external URL or a local file
let audioUrl: string;
if (/^https?:\/\//i.test(audioPath)) {
console.log('🔗 Using external audio URL...');
audioUrl = audioPath;
} else {
console.log('🔄 Uploading local audio...');
if (!fs.existsSync(audioPath)) {
throw new Error(`Audio file not found: ${audioPath}`);
}
audioUrl = await uploadAudio(audioPath);
}
console.log('🔄 Creating transcript job...');
const transcriptId = await createTranscript(audioUrl);
console.log('⏳ Waiting for transcription...');
const transcript = await pollTranscript(transcriptId);
const sessionId = getSessionId(audioPath);
saveTranscript(transcript, sessionId);
return transcript;
} catch (error: any) {
console.error('❌ Transcription error:', error.message);
throw error;
}
}
};
@@ -0,0 +1,319 @@
{
"name": "transcription",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"dependencies": {
"axios": "^1.13.2"
},
"devDependencies": {
"@types/axios": "^0.9.36",
"@types/node": "^24.10.0"
}
},
"node_modules/@types/axios": {
"version": "0.9.36",
"resolved": "https://registry.npmjs.org/@types/axios/-/axios-0.9.36.tgz",
"integrity": "sha512-NLOpedx9o+rxo/X5ChbdiX6mS1atE4WHmEEIcR9NLenRVa5HoVjAvjafwU3FPTqnZEstpoqCaW7fagqSoTDNeg==",
"dev": true,
"license": "MIT"
},
"node_modules/@types/node": {
"version": "24.10.0",
"resolved": "https://registry.npmjs.org/@types/node/-/node-24.10.0.tgz",
"integrity": "sha512-qzQZRBqkFsYyaSWXuEHc2WR9c0a0CXwiE5FWUvn7ZM+vdy1uZLfCunD38UzhuB7YN/J11ndbDBcTmOdxJo9Q7A==",
"dev": true,
"license": "MIT",
"dependencies": {
"undici-types": "~7.16.0"
}
},
"node_modules/asynckit": {
"version": "0.4.0",
"resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz",
"integrity": "sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==",
"license": "MIT"
},
"node_modules/axios": {
"version": "1.13.2",
"resolved": "https://registry.npmjs.org/axios/-/axios-1.13.2.tgz",
"integrity": "sha512-VPk9ebNqPcy5lRGuSlKx752IlDatOjT9paPlm8A7yOuW2Fbvp4X3JznJtT4f0GzGLLiWE9W8onz51SqLYwzGaA==",
"license": "MIT",
"dependencies": {
"follow-redirects": "^1.15.6",
"form-data": "^4.0.4",
"proxy-from-env": "^1.1.0"
}
},
"node_modules/call-bind-apply-helpers": {
"version": "1.0.2",
"resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
"integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
"license": "MIT",
"dependencies": {
"es-errors": "^1.3.0",
"function-bind": "^1.1.2"
},
"engines": {
"node": ">= 0.4"
}
},
"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==",
"license": "MIT",
"dependencies": {
"delayed-stream": "~1.0.0"
},
"engines": {
"node": ">= 0.8"
}
},
"node_modules/delayed-stream": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz",
"integrity": "sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==",
"license": "MIT",
"engines": {
"node": ">=0.4.0"
}
},
"node_modules/dunder-proto": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
"integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
"license": "MIT",
"dependencies": {
"call-bind-apply-helpers": "^1.0.1",
"es-errors": "^1.3.0",
"gopd": "^1.2.0"
},
"engines": {
"node": ">= 0.4"
}
},
"node_modules/es-define-property": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
"integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
"license": "MIT",
"engines": {
"node": ">= 0.4"
}
},
"node_modules/es-errors": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
"integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
"license": "MIT",
"engines": {
"node": ">= 0.4"
}
},
"node_modules/es-object-atoms": {
"version": "1.1.1",
"resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
"integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
"license": "MIT",
"dependencies": {
"es-errors": "^1.3.0"
},
"engines": {
"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==",
"license": "MIT",
"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/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"
}
],
"license": "MIT",
"engines": {
"node": ">=4.0"
},
"peerDependenciesMeta": {
"debug": {
"optional": true
}
}
},
"node_modules/form-data": {
"version": "4.0.4",
"resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
"integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
"license": "MIT",
"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/function-bind": {
"version": "1.1.2",
"resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
"integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
"license": "MIT",
"funding": {
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/get-intrinsic": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
"integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
"license": "MIT",
"dependencies": {
"call-bind-apply-helpers": "^1.0.2",
"es-define-property": "^1.0.1",
"es-errors": "^1.3.0",
"es-object-atoms": "^1.1.1",
"function-bind": "^1.1.2",
"get-proto": "^1.0.1",
"gopd": "^1.2.0",
"has-symbols": "^1.1.0",
"hasown": "^2.0.2",
"math-intrinsics": "^1.1.0"
},
"engines": {
"node": ">= 0.4"
},
"funding": {
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/get-proto": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
"integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
"license": "MIT",
"dependencies": {
"dunder-proto": "^1.0.1",
"es-object-atoms": "^1.0.0"
},
"engines": {
"node": ">= 0.4"
}
},
"node_modules/gopd": {
"version": "1.2.0",
"resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
"integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
"license": "MIT",
"engines": {
"node": ">= 0.4"
},
"funding": {
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/has-symbols": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
"integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
"license": "MIT",
"engines": {
"node": ">= 0.4"
},
"funding": {
"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==",
"license": "MIT",
"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",
"integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
"license": "MIT",
"dependencies": {
"function-bind": "^1.1.2"
},
"engines": {
"node": ">= 0.4"
}
},
"node_modules/math-intrinsics": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
"integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
"license": "MIT",
"engines": {
"node": ">= 0.4"
}
},
"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==",
"license": "MIT",
"engines": {
"node": ">= 0.6"
}
},
"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==",
"license": "MIT",
"dependencies": {
"mime-db": "1.52.0"
},
"engines": {
"node": ">= 0.6"
}
},
"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==",
"license": "MIT"
},
"node_modules/undici-types": {
"version": "7.16.0",
"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.16.0.tgz",
"integrity": "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw==",
"dev": true,
"license": "MIT"
}
}
}
@@ -0,0 +1,9 @@
{
"dependencies": {
"axios": "^1.13.2"
},
"devDependencies": {
"@types/axios": "^0.9.36",
"@types/node": "^24.10.0"
}
}
+4
View File
@@ -5,5 +5,9 @@ module.exports = {
// We are now calling the example function from the example folder
mapFunctions.get("example").function("Startup")
// 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 +1,52 @@
// services/pipeline/jobs/transcribeLatest.ts
import path from 'path';
import fs from 'fs';
import assembly from '../../modules/transcription/assembly';
/**
* Finds the most recently modified .wav file in storage/audio/
*/
function getLatestWav(): string {
const audioDir = path.join(process.cwd(), 'storage', 'audio');
const files = fs.readdirSync(audioDir).filter(f => f.toLowerCase().endsWith('.wav'));
if (files.length === 0) throw new Error('⚠️ No .wav file found in storage/audio');
const newest = files
.map(f => ({ f, t: fs.statSync(path.join(audioDir, f)).mtimeMs }))
.sort((a, b) => b.t - a.t)[0].f;
return path.join(audioDir, newest);
}
/**
* Full transcription pipeline according to the defined workflow:
* 1. Audio Upload → AssemblyAI
* 2. Job Creation (transcript_id)
* 3. Polling Status (queued → processing → completed)
* 4. Download Transcript JSON
* 5. Storage: /transcripts/{session_id}.json
*/
async function main() {
const audioPath = getLatestWav();
console.log('1️⃣ Audio Upload → AssemblyAI');
console.log(' Source:', audioPath);
console.log('2️⃣ Job Creation (transcript_id)');
console.log('3️⃣ Polling Status (queued → processing → completed)');
console.log('4️⃣ Download Transcript JSON');
console.log('5️⃣ Storage: /transcripts/{session_id}.json');
// Execute the transcription process via the AssemblyAI module
const result = await assembly.run(audioPath);
console.log('✅ Transcription completed successfully');
console.log('🆔 Transcript ID:', result.id);
console.log('📁 Transcript file saved under: storage/transcripts/');
}
// Entry point
main().catch((err) => {
console.error('❌ Transcription pipeline failed:', err.message || err);
process.exit(1);
});