StillHammer/videotomp3transcriptor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

base: StillHammer:ce32ae313406e0f5cff6787b35b25e313c64bdf1
Branches Tags
StillHammer:main
StillHammer:music-service-v2
..
compare: StillHammer:23bb4cd2d9c7b5bf041d6c9ed483572bcad11467
Branches Tags
StillHammer:music-service-v2
StillHammer:main

No commits in common. "ce32ae313406e0f5cff6787b35b25e313c64bdf1" and "23bb4cd2d9c7b5bf041d6c9ed483572bcad11467" have entirely different histories.
ce32ae3134 ... 23bb4cd2d9

15 changed files with 4626 additions and 5457 deletions
Show Stats Expand all files Collapse all files

9
.claude/settings.local.json
View File

@ -1,9 +0,0 @@
{
"permissions": {
"allow": [
"Bash(npm run server:*)"
],
"deny": [],
"ask": []
}
}

128
CLAUDE.md
View File

@ -1,128 +0,0 @@
# Video to MP3 Transcriptor - Instructions pour Claude
## À propos du projet
Ce projet est une API Node.js/Express pour télécharger des vidéos YouTube en MP3, les transcrire, les traduire et les résumer.
## Documentation
### Documentation API
La documentation complète de l'API se trouve dans **`docs/API.md`**.
**IMPORTANT** : Cette documentation doit TOUJOURS être maintenue à jour. Chaque fois qu'un endpoint est modifié, ajouté ou supprimé, la documentation doit être mise à jour en conséquence.
### Responsabilités de maintenance de la documentation
Quand tu modifies le code, tu DOIS mettre à jour `docs/API.md` si :
- Un nouvel endpoint est ajouté
- Un endpoint existant est modifié (paramètres, réponses, etc.)
- Un endpoint est supprimé
- Les modèles par défaut changent
- De nouveaux paramètres sont ajoutés
- Le format des réponses change
## Structure du projet
```
videotoMP3Transcriptor/
├── docs/
│ └── API.md # Documentation complète de l'API
├── src/
│ ├── server.js # Serveur Express et routes API
│ ├── services/
│ │ ├── youtube.js # Téléchargement YouTube
│ │ ├── transcription.js # Transcription OpenAI
│ │ ├── translation.js # Traduction GPT
│ │ └── summarize.js # Résumé GPT-5.1
│ └── cli.js # Interface en ligne de commande
├── public/ # Interface web (si présente)
├── output/ # Répertoire de sortie par défaut
├── .env # Variables d'environnement
└── package.json
```
## Configuration
### Port du serveur
- Port par défaut : **8888**
- Configurable via `process.env.PORT` dans `.env`
### Modèles par défaut
- **Transcription** : `gpt-4o-mini-transcribe`
- **Résumé** : `gpt-5.1`
- **Traduction** : `gpt-4o-mini` (hardcodé)
### Variables d'environnement requises
```env
OPENAI_API_KEY=sk-...
PORT=8888 # optionnel
OUTPUT_DIR=./output # optionnel
```
## Commandes importantes
```bash
# Lancer le serveur
npm run server
# Lancer le CLI
npm run cli
# Installer les dépendances
npm install
```
## Points d'attention
### Paramètres outputPath
Tous les endpoints supportent maintenant un paramètre `outputPath` optionnel pour spécifier un répertoire de sortie personnalisé. Si non spécifié, le répertoire par défaut `OUTPUT_DIR` est utilisé.
### Modèles de transcription disponibles
- `gpt-4o-mini-transcribe` (par défaut) - Rapide et économique
- `gpt-4o-transcribe` - Qualité supérieure
- `whisper-1` - Modèle original Whisper (supporte plus de formats)
### Formats de sortie
- **Transcription** : txt, json, srt, vtt (selon le modèle)
- **Traduction** : txt
- **Résumé** : txt
## Règles de développement
1. **Documentation d'abord** : Avant de modifier un endpoint, vérifie `docs/API.md`
2. **Après modification** : Mets à jour immédiatement `docs/API.md`
3. **Tests** : Redémarre le serveur après chaque modification
4. **Cohérence** : Garde la même structure de réponse pour tous les endpoints similaires
## Architecture des endpoints
### Endpoints streaming (SSE)
- `/download-stream`
- `/process-stream`
- `/summarize-stream`
Ces endpoints utilisent Server-Sent Events pour envoyer des mises à jour de progression en temps réel.
### Endpoints non-streaming
- `/download`
- `/process`
- Tous les endpoints POST avec upload de fichiers
Ces endpoints retournent une réponse unique une fois le traitement terminé.
## Maintenance
Lors de l'ajout de nouvelles fonctionnalités :
1. Implémente la fonctionnalité dans le service approprié (`src/services/`)
2. Ajoute les routes dans `src/server.js`
3. **Mets à jour `docs/API.md` IMMÉDIATEMENT**
4. Teste l'endpoint avec curl ou Postman
5. Vérifie que la documentation est claire et complète
## Notes importantes
- Le serveur doit toujours être sur le port **8888**
- Les clés API OpenAI sont requises pour transcription/traduction/résumé
- Le répertoire `output/` est créé automatiquement si inexistant
- Les fichiers uploadés sont stockés dans `OUTPUT_DIR`
- Les vidéos YouTube sont téléchargées en MP3 automatiquement

561
docs/API.md
View File

@ -1,561 +0,0 @@
# API Documentation - Video to MP3 Transcriptor
## Base URL
```
http://localhost:8888
```
## Table of Contents
- [Health & Info](#health--info)
- [Download Endpoints](#download-endpoints)
- [Transcription Endpoints](#transcription-endpoints)
- [Translation Endpoints](#translation-endpoints)
- [Summarization Endpoints](#summarization-endpoints)
- [File Management](#file-management)
---
## Health & Info
### GET /health
Health check endpoint.
**Response:**
```json
{
"status": "ok",
"timestamp": "2025-11-28T12:00:00.000Z"
}
```
### GET /api
Get API information and available endpoints.
**Response:**
```json
{
"name": "Video to MP3 Transcriptor API",
"version": "1.0.0",
"endpoints": { ... }
}
```
### GET /info
Get information about a YouTube video or playlist.
**Query Parameters:**
- `url` (required): YouTube URL
**Example:**
```bash
curl "http://localhost:8888/info?url=https://www.youtube.com/watch?v=VIDEO_ID"
```
**Response:**
```json
{
"success": true,
"title": "Video Title",
"type": "video",
"duration": 300,
"channel": "Channel Name",
"videoCount": 1
}
```
---
## Download Endpoints
### GET /download-stream
Download YouTube video(s) to MP3 with Server-Sent Events (SSE) progress updates.
**Query Parameters:**
- `url` (required): YouTube URL
- `outputPath` (optional): Custom output directory path
**Example:**
```bash
curl "http://localhost:8888/download-stream?url=https://www.youtube.com/watch?v=VIDEO_ID"
```
**SSE Events:**
- `info`: Video/playlist information
- `progress`: Download progress updates
- `video-complete`: Individual video completion
- `complete`: All downloads complete
- `error`: Error occurred
### POST /download
Download YouTube video(s) to MP3 (non-streaming).
**Body Parameters:**
```json
{
"url": "https://www.youtube.com/watch?v=VIDEO_ID",
"outputPath": "./custom/path" // optional
}
```
**Example:**
```bash
curl -X POST http://localhost:8888/download \
-H "Content-Type: application/json" \
-d '{"url":"https://www.youtube.com/watch?v=VIDEO_ID"}'
```
**Response:**
```json
{
"success": true,
"playlistTitle": null,
"totalVideos": 1,
"successCount": 1,
"failCount": 0,
"videos": [
{
"success": true,
"title": "Video Title",
"filePath": "./output/video.mp3",
"fileUrl": "/files/video.mp3"
}
]
}
```
---
## Transcription Endpoints
### POST /transcribe
Transcribe an existing audio file.
**Body Parameters:**
```json
{
"filePath": "./output/audio.mp3",
"language": "en", // optional (auto-detect if not specified)
"format": "txt", // optional: txt, json, srt, vtt
"model": "gpt-4o-mini-transcribe", // optional: gpt-4o-mini-transcribe (default), gpt-4o-transcribe, whisper-1
"outputPath": "./custom/path" // optional
}
```
**Available Models:**
- `gpt-4o-mini-transcribe` (default) - Fast and cost-effective
- `gpt-4o-transcribe` - Higher quality
- `whisper-1` - Original Whisper model (supports more formats)
**Example:**
```bash
curl -X POST http://localhost:8888/transcribe \
-H "Content-Type: application/json" \
-d '{
"filePath": "./output/audio.mp3",
"language": "en",
"model": "gpt-4o-mini-transcribe"
}'
```
**Response:**
```json
{
"success": true,
"filePath": "./output/audio.mp3",
"transcriptionPath": "./output/audio.txt",
"transcriptionUrl": "/files/audio.txt",
"text": "Transcribed text content..."
}
```
### POST /upload-transcribe
Upload and transcribe audio files.
**Form Data:**
- `files`: Audio file(s) (multiple files supported, max 50)
- `language`: Language code (optional)
- `model`: Transcription model (optional, default: gpt-4o-mini-transcribe)
- `outputPath`: Custom output directory (optional)
**Example:**
```bash
curl -X POST http://localhost:8888/upload-transcribe \
-F "files=@audio1.mp3" \
-F "files=@audio2.mp3" \
-F "language=en" \
-F "model=gpt-4o-mini-transcribe"
```
**Response:**
```json
{
"success": true,
"totalFiles": 2,
"successCount": 2,
"failCount": 0,
"results": [
{
"success": true,
"fileName": "audio1.mp3",
"transcriptionPath": "./output/audio1.txt",
"transcriptionUrl": "/files/audio1.txt",
"text": "Transcription..."
}
]
}
```
### GET /process-stream
Download + Transcribe with SSE progress updates.
**Query Parameters:**
- `url` (required): YouTube URL
- `language` (optional): Language code
- `model` (optional): Transcription model (default: gpt-4o-mini-transcribe)
- `outputPath` (optional): Custom output directory
**Example:**
```bash
curl "http://localhost:8888/process-stream?url=https://www.youtube.com/watch?v=VIDEO_ID&language=en&model=gpt-4o-mini-transcribe"
```
**SSE Events:**
- `info`: Video information
- `progress`: Progress updates (downloading or transcribing)
- `video-complete`: Download complete
- `transcribe-complete`: Transcription complete
- `complete`: All operations complete
- `error`: Error occurred
### POST /process
Download + Transcribe (non-streaming).
**Body Parameters:**
```json
{
"url": "https://www.youtube.com/watch?v=VIDEO_ID",
"language": "en", // optional
"format": "txt", // optional
"model": "gpt-4o-mini-transcribe", // optional
"outputPath": "./custom/path" // optional
}
```
**Example:**
```bash
curl -X POST http://localhost:8888/process \
-H "Content-Type: application/json" \
-d '{
"url": "https://www.youtube.com/watch?v=VIDEO_ID",
"language": "en",
"model": "gpt-4o-mini-transcribe"
}'
```
**Response:**
```json
{
"success": true,
"playlistTitle": null,
"totalVideos": 1,
"downloadedCount": 1,
"transcribedCount": 1,
"results": [
{
"title": "Video Title",
"downloadSuccess": true,
"audioPath": "./output/video.mp3",
"audioUrl": "/files/video.mp3",
"transcriptionSuccess": true,
"transcriptionPath": "./output/video.txt",
"transcriptionUrl": "/files/video.txt",
"text": "Transcription..."
}
]
}
```
---
## Translation Endpoints
### GET /languages
Get available translation languages.
**Response:**
```json
{
"languages": {
"en": "English",
"fr": "French",
"es": "Spanish",
"de": "German",
"zh": "Chinese",
"ja": "Japanese",
...
}
}
```
### POST /translate
Translate text.
**Body Parameters:**
```json
{
"text": "Text to translate",
"targetLang": "fr", // required: target language code
"sourceLang": "en" // optional: source language (auto-detect if not specified)
}
```
**Example:**
```bash
curl -X POST http://localhost:8888/translate \
-H "Content-Type: application/json" \
-d '{
"text": "Hello, how are you?",
"targetLang": "fr"
}'
```
**Response:**
```json
{
"success": true,
"originalText": "Hello, how are you?",
"translatedText": "Bonjour, comment allez-vous ?",
"targetLanguage": "French",
"sourceLanguage": "auto-detected",
"chunks": 1
}
```
### POST /translate-file
Translate uploaded text files.
**Form Data:**
- `files`: Text file(s) (.txt, multiple files supported, max 50)
- `targetLang`: Target language code (required)
- `sourceLang`: Source language code (optional)
- `outputPath`: Custom output directory (optional)
**Example:**
```bash
curl -X POST http://localhost:8888/translate-file \
-F "files=@document.txt" \
-F "targetLang=fr" \
-F "sourceLang=en"
```
**Response:**
```json
{
"success": true,
"totalFiles": 1,
"successCount": 1,
"failCount": 0,
"results": [
{
"success": true,
"fileName": "document.txt",
"translationPath": "./output/document_fr.txt",
"translationUrl": "/files/document_fr.txt",
"translatedText": "Translated content..."
}
]
}
```
---
## Summarization Endpoints
### GET /summary-styles
Get available summary styles.
**Response:**
```json
{
"styles": {
"concise": "A brief summary capturing main points",
"detailed": "A comprehensive summary with nuances",
"bullet": "Key points as bullet points"
}
}
```
### POST /summarize
Summarize text using GPT-5.1.
**Body Parameters:**
```json
{
"text": "Long text to summarize...",
"style": "concise", // optional: concise (default), detailed, bullet
"language": "same", // optional: 'same' (default) or language code
"model": "gpt-5.1" // optional: default is gpt-5.1
}
```
**Example:**
```bash
curl -X POST http://localhost:8888/summarize \
-H "Content-Type: application/json" \
-d '{
"text": "Long article content...",
"style": "bullet",
"language": "same"
}'
```
**Response:**
```json
{
"success": true,
"summary": "Summary content...",
"model": "gpt-5.1",
"style": "bullet",
"inputLength": 5000,
"chunks": 1
}
```
### POST /summarize-file
Summarize uploaded text files using GPT-5.1.
**Form Data:**
- `files`: Text file(s) (.txt, multiple files supported, max 50)
- `style`: Summary style (optional, default: concise)
- `language`: Output language (optional, default: same)
- `model`: AI model (optional, default: gpt-5.1)
- `outputPath`: Custom output directory (optional)
**Example:**
```bash
curl -X POST http://localhost:8888/summarize-file \
-F "files=@article.txt" \
-F "style=detailed" \
-F "language=same"
```
**Response:**
```json
{
"success": true,
"totalFiles": 1,
"successCount": 1,
"failCount": 0,
"results": [
{
"success": true,
"fileName": "article.txt",
"summaryPath": "./output/article_summary.txt",
"summaryUrl": "/files/article_summary.txt",
"summary": "Summary content...",
"model": "gpt-5.1",
"chunks": 1
}
]
}
```
### GET /summarize-stream
Full pipeline: Download -> Transcribe -> Summarize with SSE progress.
**Query Parameters:**
- `url` (required): YouTube URL
- `style` (optional): Summary style (default: concise)
- `language` (optional): Output language (default: same)
- `model` (optional): Transcription model (default: gpt-4o-mini-transcribe)
- `outputPath` (optional): Custom output directory
**Example:**
```bash
curl "http://localhost:8888/summarize-stream?url=https://www.youtube.com/watch?v=VIDEO_ID&style=bullet&model=gpt-4o-mini-transcribe"
```
**SSE Events:**
- `info`: Video information
- `progress`: Progress updates (downloading, transcribing, or summarizing)
- `video-complete`: Download complete
- `transcribe-complete`: Transcription complete
- `summarize-complete`: Summary complete
- `complete`: All operations complete
- `error`: Error occurred
---
## File Management
### GET /files-list
List all downloaded/generated files.
**Example:**
```bash
curl http://localhost:8888/files-list
```
**Response:**
```json
{
"files": [
{
"name": "video.mp3",
"url": "/files/video.mp3",
"path": "./output/video.mp3"
},
{
"name": "video.txt",
"url": "/files/video.txt",
"path": "./output/video.txt"
}
]
}
```
### GET /files/:filename
Serve a specific file.
**Example:**
```bash
curl http://localhost:8888/files/video.mp3 --output video.mp3
```
---
## Error Responses
All endpoints return error responses in the following format:
```json
{
"error": "Error message describing what went wrong"
}
```
Common HTTP status codes:
- `400` - Bad Request (missing required parameters)
- `500` - Internal Server Error (processing failed)
---
## Notes
### Output Paths
All endpoints that support `outputPath` parameter:
- If not specified, files are saved to the default `OUTPUT_DIR` (./output)
- If specified, files are saved to the custom path provided
### Models
- **Transcription**: Default is `gpt-4o-mini-transcribe` (cost-effective)
- **Summarization**: Default is `gpt-5.1` (latest GPT model)
- **Translation**: Uses `gpt-4o-mini` (hardcoded)
### File Formats
- **Audio**: MP3, WAV, M4A, OGG, FLAC
- **Text**: TXT files
- **Transcription outputs**: TXT, JSON, SRT, VTT (depending on model)
### API Key
Ensure `OPENAI_API_KEY` is set in your `.env` file for transcription, translation, and summarization features to work.

1
nul
View File

@ -1 +0,0 @@
/usr/bin/bash: line 1: del: command not found

54
src/server.js
View File

@ -14,7 +14,7 @@ import { convertToMP3, convertMultipleToMP3, getSupportedFormats } from './servi
dotenv.config(); dotenv.config();
const app = express(); const app = express();
const PORT = process.env.PORT || 8888; const PORT = process.env.PORT || 3000;
const OUTPUT_DIR = process.env.OUTPUT_DIR || './output'; const OUTPUT_DIR = process.env.OUTPUT_DIR || './output';
// Ensure output directory exists // Ensure output directory exists
@ -151,10 +151,10 @@ app.get('/info', async (req, res) => {
/** /**
* GET /download-stream * GET /download-stream
* Download with SSE progress updates * Download with SSE progress updates
* Query: url (required), outputPath (optional) * Query: url (required)
*/ */
app.get('/download-stream', async (req, res) => { app.get('/download-stream', async (req, res) => {
const { url, outputPath } = req.query; const { url } = req.query;
if (!url) { if (!url) {
return res.status(400).json({ error: 'URL parameter required' }); return res.status(400).json({ error: 'URL parameter required' });
@ -195,7 +195,7 @@ app.get('/download-stream', async (req, res) => {
let videoStartTime = Date.now(); let videoStartTime = Date.now();
const result = await download(url, { const result = await download(url, {
outputDir: outputPath || OUTPUT_DIR, outputDir: OUTPUT_DIR,
onDownloadProgress: (progress) => { onDownloadProgress: (progress) => {
// Calculate overall progress // Calculate overall progress
const videoProgress = progress.percent || 0; const videoProgress = progress.percent || 0;
@ -274,12 +274,11 @@ app.get('/download-stream', async (req, res) => {
/** /**
* POST /download * POST /download
* Download a video or playlist as MP3 (non-streaming version) * Download a video or playlist as MP3 (non-streaming version)
* Body: { url: string, outputPath?: string } * Body: { url: string, outputDir?: string }
*/ */
app.post('/download', async (req, res) => { app.post('/download', async (req, res) => {
try { try {
const { url, outputPath } = req.body; const { url, outputDir = OUTPUT_DIR } = req.body;
const outputDir = outputPath || OUTPUT_DIR;
if (!url) { if (!url) {
return res.status(400).json({ error: 'URL required in request body' }); return res.status(400).json({ error: 'URL required in request body' });
@ -310,11 +309,11 @@ app.post('/download', async (req, res) => {
/** /**
* POST /transcribe * POST /transcribe
* Transcribe an existing audio file * Transcribe an existing audio file
* Body: { filePath: string, language?: string, format?: string, outputPath?: string } * Body: { filePath: string, language?: string, format?: string }
*/ */
app.post('/transcribe', async (req, res) => { app.post('/transcribe', async (req, res) => {
try { try {
const { filePath, language, format = 'txt', model = 'gpt-4o-mini-transcribe', outputPath } = req.body; const { filePath, language, format = 'txt', model = 'gpt-4o-transcribe' } = req.body;
if (!filePath) { if (!filePath) {
return res.status(400).json({ error: 'filePath required in request body' }); return res.status(400).json({ error: 'filePath required in request body' });
@ -330,7 +329,6 @@ app.post('/transcribe', async (req, res) => {
responseFormat: format === 'txt' ? 'text' : format, responseFormat: format === 'txt' ? 'text' : format,
outputFormat: format, outputFormat: format,
model, model,
outputDir: outputPath,
}); });
res.json({ res.json({
@ -348,7 +346,6 @@ app.post('/transcribe', async (req, res) => {
/** /**
* POST /upload-transcribe * POST /upload-transcribe
* Upload audio files and transcribe them * Upload audio files and transcribe them
* Body: { language?: string, model?: string, outputPath?: string }
*/ */
app.post('/upload-transcribe', upload.array('files', 50), async (req, res) => { app.post('/upload-transcribe', upload.array('files', 50), async (req, res) => {
try { try {
@ -360,7 +357,7 @@ app.post('/upload-transcribe', upload.array('files', 50), async (req, res) => {
return res.status(400).json({ error: 'No files uploaded' }); return res.status(400).json({ error: 'No files uploaded' });
} }
const { language, model = 'gpt-4o-mini-transcribe', outputPath } = req.body; const { language, model = 'gpt-4o-transcribe' } = req.body;
const results = []; const results = [];
console.log(`Transcribing ${req.files.length} uploaded files with model ${model}`); console.log(`Transcribing ${req.files.length} uploaded files with model ${model}`);
@ -375,7 +372,6 @@ app.post('/upload-transcribe', upload.array('files', 50), async (req, res) => {
responseFormat: 'text', responseFormat: 'text',
outputFormat: 'txt', outputFormat: 'txt',
model, model,
outputDir: outputPath,
}); });
results.push({ results.push({
@ -475,10 +471,10 @@ app.get('/supported-formats', (req, res) => {
/** /**
* GET /process-stream * GET /process-stream
* Download and transcribe with SSE progress updates * Download and transcribe with SSE progress updates
* Query: url, language?, model?, outputPath? * Query: url, language?, model?
*/ */
app.get('/process-stream', async (req, res) => { app.get('/process-stream', async (req, res) => {
const { url, language, model = 'gpt-4o-mini-transcribe', outputPath } = req.query; const { url, language, model = 'gpt-4o-transcribe' } = req.query;
if (!url) { if (!url) {
return res.status(400).json({ error: 'URL parameter required' }); return res.status(400).json({ error: 'URL parameter required' });
@ -523,7 +519,7 @@ app.get('/process-stream', async (req, res) => {
let videoStartTime = Date.now(); let videoStartTime = Date.now();
const downloadResult = await download(url, { const downloadResult = await download(url, {
outputDir: outputPath || OUTPUT_DIR, outputDir: OUTPUT_DIR,
onDownloadProgress: (progress) => { onDownloadProgress: (progress) => {
const videoProgress = progress.percent || 0; const videoProgress = progress.percent || 0;
// Download is 50% of total, transcribe is other 50% // Download is 50% of total, transcribe is other 50%
@ -583,7 +579,6 @@ app.get('/process-stream', async (req, res) => {
responseFormat: 'text', responseFormat: 'text',
outputFormat: 'txt', outputFormat: 'txt',
model, model,
outputDir: outputPath,
}); });
transcribeResults.push(result); transcribeResults.push(result);
videosTranscribed++; videosTranscribed++;
@ -647,12 +642,11 @@ app.get('/process-stream', async (req, res) => {
/** /**
* POST /process * POST /process
* Download and transcribe a video or playlist (non-streaming) * Download and transcribe a video or playlist (non-streaming)
* Body: { url: string, language?: string, format?: string, outputPath?: string } * Body: { url: string, language?: string, format?: string }
*/ */
app.post('/process', async (req, res) => { app.post('/process', async (req, res) => {
try { try {
const { url, language, format = 'txt', outputPath, model = 'gpt-4o-mini-transcribe' } = req.body; const { url, language, format = 'txt', outputDir = OUTPUT_DIR, model = 'gpt-4o-transcribe' } = req.body;
const outputDir = outputPath || OUTPUT_DIR;
if (!url) { if (!url) {
return res.status(400).json({ error: 'URL required in request body' }); return res.status(400).json({ error: 'URL required in request body' });
@ -676,7 +670,6 @@ app.post('/process', async (req, res) => {
responseFormat: format === 'txt' ? 'text' : format, responseFormat: format === 'txt' ? 'text' : format,
outputFormat: format, outputFormat: format,
model, model,
outputDir,
}); });
// Combine results // Combine results
@ -778,7 +771,6 @@ app.post('/translate', async (req, res) => {
/** /**
* POST /translate-file * POST /translate-file
* Translate uploaded text files * Translate uploaded text files
* Body: { targetLang: string, sourceLang?: string, outputPath?: string }
*/ */
app.post('/translate-file', uploadText.array('files', 50), async (req, res) => { app.post('/translate-file', uploadText.array('files', 50), async (req, res) => {
try { try {
@ -790,7 +782,7 @@ app.post('/translate-file', uploadText.array('files', 50), async (req, res) => {
return res.status(400).json({ error: 'No files uploaded' }); return res.status(400).json({ error: 'No files uploaded' });
} }
const { targetLang, sourceLang, outputPath } = req.body; const { targetLang, sourceLang } = req.body;
if (!targetLang) { if (!targetLang) {
return res.status(400).json({ error: 'targetLang required' }); return res.status(400).json({ error: 'targetLang required' });
@ -804,7 +796,7 @@ app.post('/translate-file', uploadText.array('files', 50), async (req, res) => {
console.log(`[${i + 1}/${req.files.length}] Translating: ${file.originalname}`); console.log(`[${i + 1}/${req.files.length}] Translating: ${file.originalname}`);
try { try {
const result = await translateFile(file.path, targetLang, sourceLang || null, outputPath); const result = await translateFile(file.path, targetLang, sourceLang || null);
results.push({ results.push({
success: true, success: true,
fileName: file.originalname, fileName: file.originalname,
@ -874,7 +866,6 @@ app.post('/summarize', async (req, res) => {
/** /**
* POST /summarize-file * POST /summarize-file
* Summarize uploaded text files using GPT-5.1 * Summarize uploaded text files using GPT-5.1
* Body: { style?: string, language?: string, model?: string, outputPath?: string }
*/ */
app.post('/summarize-file', uploadText.array('files', 50), async (req, res) => { app.post('/summarize-file', uploadText.array('files', 50), async (req, res) => {
try { try {
@ -886,7 +877,7 @@ app.post('/summarize-file', uploadText.array('files', 50), async (req, res) => {
return res.status(400).json({ error: 'No files uploaded' }); return res.status(400).json({ error: 'No files uploaded' });
} }
const { style = 'concise', language = 'same', model = 'gpt-5.1', outputPath } = req.body; const { style = 'concise', language = 'same', model = 'gpt-5.1' } = req.body;
const results = []; const results = [];
console.log(`Summarizing ${req.files.length} files with ${model}`); console.log(`Summarizing ${req.files.length} files with ${model}`);
@ -896,7 +887,7 @@ app.post('/summarize-file', uploadText.array('files', 50), async (req, res) => {
console.log(`[${i + 1}/${req.files.length}] Summarizing: ${file.originalname}`); console.log(`[${i + 1}/${req.files.length}] Summarizing: ${file.originalname}`);
try { try {
const result = await summarizeFile(file.path, { style, language, model, outputDir: outputPath }); const result = await summarizeFile(file.path, { style, language, model });
results.push({ results.push({
success: true, success: true,
fileName: file.originalname, fileName: file.originalname,
@ -931,10 +922,10 @@ app.post('/summarize-file', uploadText.array('files', 50), async (req, res) => {
/** /**
* GET /summarize-stream * GET /summarize-stream
* Full pipeline: Download -> Transcribe -> Summarize with SSE progress * Full pipeline: Download -> Transcribe -> Summarize with SSE progress
* Query: url, style?, language?, model?, outputPath? * Query: url, style?, language?, model?
*/ */
app.get('/summarize-stream', async (req, res) => { app.get('/summarize-stream', async (req, res) => {
const { url, style = 'concise', language = 'same', model = 'gpt-4o-mini-transcribe', outputPath } = req.query; const { url, style = 'concise', language = 'same', model = 'gpt-4o-transcribe' } = req.query;
if (!url) { if (!url) {
return res.status(400).json({ error: 'URL parameter required' }); return res.status(400).json({ error: 'URL parameter required' });
@ -977,7 +968,7 @@ app.get('/summarize-stream', async (req, res) => {
let videosDownloaded = 0; let videosDownloaded = 0;
const downloadResult = await download(url, { const downloadResult = await download(url, {
outputDir: outputPath || OUTPUT_DIR, outputDir: OUTPUT_DIR,
onDownloadProgress: (progress) => { onDownloadProgress: (progress) => {
const videoProgress = progress.percent || 0; const videoProgress = progress.percent || 0;
const overallPercent = ((videosDownloaded + (videoProgress / 100)) / totalVideos) * 33; const overallPercent = ((videosDownloaded + (videoProgress / 100)) / totalVideos) * 33;
@ -1028,7 +1019,6 @@ app.get('/summarize-stream', async (req, res) => {
responseFormat: 'text', responseFormat: 'text',
outputFormat: 'txt', outputFormat: 'txt',
model, model,
outputDir: outputPath,
}); });
transcribeResults.push({ ...result, title: video.title, success: true }); transcribeResults.push({ ...result, title: video.title, success: true });
@ -1069,7 +1059,7 @@ app.get('/summarize-stream', async (req, res) => {
}); });
try { try {
const result = await summarizeFile(transcription.transcriptionPath, { style, language, model: 'gpt-5.1', outputDir: outputPath }); const result = await summarizeFile(transcription.transcriptionPath, { style, language, model: 'gpt-5.1' });
summaryResults.push({ summaryResults.push({
title: transcription.title, title: transcription.title,
success: true, success: true,

6
src/services/summarize.js
View File

@ -164,13 +164,11 @@ export async function summarizeFile(filePath, options = {}) {
throw new Error(`File not found: ${filePath}`); throw new Error(`File not found: ${filePath}`);
} }
const { outputDir, ...otherOptions } = options;
const text = fs.readFileSync(filePath, 'utf-8'); const text = fs.readFileSync(filePath, 'utf-8');
const result = await summarizeText(text, otherOptions); const result = await summarizeText(text, options);
// Save summary to file // Save summary to file
const dir = outputDir || path.dirname(filePath); const dir = path.dirname(filePath);
const baseName = path.basename(filePath, path.extname(filePath)); const baseName = path.basename(filePath, path.extname(filePath));
const summaryPath = path.join(dir, `${baseName}_summary.txt`); const summaryPath = path.join(dir, `${baseName}_summary.txt`);

2
src/services/transcription.js
View File

@ -23,7 +23,7 @@ const MODELS = {
}, },
}; };
const DEFAULT_MODEL = 'gpt-4o-mini-transcribe'; const DEFAULT_MODEL = 'gpt-4o-transcribe';
/** /**
* Get OpenAI client (lazy initialization) * Get OpenAI client (lazy initialization)

9
src/services/translation.js
View File

@ -207,9 +207,8 @@ export async function translateText(text, targetLang, sourceLang = null) {
* @param {string} filePath - Path to text file * @param {string} filePath - Path to text file
* @param {string} targetLang - Target language code * @param {string} targetLang - Target language code
* @param {string} sourceLang - Source language code (optional) * @param {string} sourceLang - Source language code (optional)
* @param {string} outputDir - Output directory (optional)
*/ */
export async function translateFile(filePath, targetLang, sourceLang = null, outputDir = null) { export async function translateFile(filePath, targetLang, sourceLang = null) {
if (!fs.existsSync(filePath)) { if (!fs.existsSync(filePath)) {
throw new Error(`File not found: ${filePath}`); throw new Error(`File not found: ${filePath}`);
} }
@ -220,7 +219,7 @@ export async function translateFile(filePath, targetLang, sourceLang = null, out
// Save translation // Save translation
const baseName = path.basename(filePath, path.extname(filePath)); const baseName = path.basename(filePath, path.extname(filePath));
const outputPath = path.join( const outputPath = path.join(
outputDir || path.dirname(filePath), path.dirname(filePath),
`${baseName}_${targetLang}.txt` `${baseName}_${targetLang}.txt`
); );
@ -236,7 +235,7 @@ export async function translateFile(filePath, targetLang, sourceLang = null, out
/** /**
* Translate multiple files * Translate multiple files
*/ */
export async function translateMultiple(filePaths, targetLang, sourceLang = null, outputDir = null, onProgress = null) { export async function translateMultiple(filePaths, targetLang, sourceLang = null, onProgress = null) {
const results = []; const results = [];
for (let i = 0; i < filePaths.length; i++) { for (let i = 0; i < filePaths.length; i++) {
@ -249,7 +248,7 @@ export async function translateMultiple(filePaths, targetLang, sourceLang = null
console.log(`[${i + 1}/${filePaths.length}] Translating: ${path.basename(filePath)}`); console.log(`[${i + 1}/${filePaths.length}] Translating: ${path.basename(filePath)}`);
try { try {
const result = await translateFile(filePath, targetLang, sourceLang, outputDir); const result = await translateFile(filePath, targetLang, sourceLang);
results.push(result); results.push(result);
} catch (error) { } catch (error) {
console.error(`Failed to translate ${filePath}: ${error.message}`); console.error(`Failed to translate ${filePath}: ${error.message}`);

61
start-server.bat
View File

@ -1,61 +0,0 @@
@echo off
REM Video to MP3 Transcriptor Server Starter
REM This script starts the API server on port 8888
echo ==========================================
echo Video to MP3 Transcriptor API
echo ==========================================
echo.
REM Check if node is installed
where node >nul 2>nul
if %ERRORLEVEL% NEQ 0 (
echo Error: Node.js is not installed
echo Please install Node.js from https://nodejs.org/
pause
exit /b 1
)
REM Check if npm is installed
where npm >nul 2>nul
if %ERRORLEVEL% NEQ 0 (
echo Error: npm is not installed
echo Please install npm
pause
exit /b 1
)
REM Check if .env file exists
if not exist .env (
echo Warning: .env file not found
echo Creating .env file...
(
echo OPENAI_API_KEY=
echo PORT=8888
echo OUTPUT_DIR=./output
) > .env
echo.
echo Please edit .env and add your OPENAI_API_KEY
echo.
)
REM Check if node_modules exists
if not exist node_modules (
echo Installing dependencies...
call npm install
echo.
)
REM Kill any process using port 8888
echo Checking port 8888...
npx kill-port 8888 >nul 2>nul
echo.
echo Starting server on http://localhost:8888
echo Press Ctrl+C to stop the server
echo.
echo ==========================================
echo.
REM Start the server
call npm run server

58
start-server.sh
View File

@ -1,58 +0,0 @@
#!/bin/bash
# Video to MP3 Transcriptor Server Starter
# This script starts the API server on port 8888
echo "=========================================="
echo "Video to MP3 Transcriptor API"
echo "=========================================="
echo ""
# Check if node is installed
if ! command -v node &> /dev/null
then
echo "Error: Node.js is not installed"
echo "Please install Node.js from https://nodejs.org/"
exit 1
fi
# Check if npm is installed
if ! command -v npm &> /dev/null
then
echo "Error: npm is not installed"
echo "Please install npm"
exit 1
fi
# Check if .env file exists
if [ ! -f .env ]; then
echo "Warning: .env file not found"
echo "Creating .env file..."
echo "OPENAI_API_KEY=" > .env
echo "PORT=8888" >> .env
echo "OUTPUT_DIR=./output" >> .env
echo ""
echo "Please edit .env and add your OPENAI_API_KEY"
echo ""
fi
# Check if node_modules exists
if [ ! -d "node_modules" ]; then
echo "Installing dependencies..."
npm install
echo ""
fi
# Kill any process using port 8888
echo "Checking port 8888..."
npx kill-port 8888 2>/dev/null
echo ""
echo "Starting server on http://localhost:8888"
echo "Press Ctrl+C to stop the server"
echo ""
echo "=========================================="
echo ""
# Start the server
npm run server