Files
Socialflow/server/services/ttsSync.ts
T
MichaelandClaude Opus 4.7 37aba33425 fix: precise TTS word-boundary timing and remove wasted sync calculations
- ffmpeg-service/main.py: replace ffsubsync path with exact word-boundary timing from edge_tts for TTS subtitles. Karaoke styling preserved.
- server/services/ttsSync.ts: fix word count to match TTS-cleaned text, remove artificial punctuationPause subtraction, strip punctuation tokens from count.
- server/routes/reels.ts: remove redundant ttsSyncService calls in preview/background; word_duration is ignored by Python, these only wasted TTS generations.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-04 13:13:55 +02:00

72 lines
2.2 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import { ffmpegService } from './ffmpeg';
import * as musicMetadata from 'music-metadata';
export interface SyncTiming {
wordDuration: number;
audioDuration: number;
wordCount: number;
punctuationPause: number;
isHealthy: boolean;
warnings: string[];
}
export class TtsSyncService {
/**
* Calcule le word_duration optimal pour synchroniser l'affichage du texte
* avec la durée réelle de la voix TTS générée.
*/
async calculateSyncTiming(text: string, voice: string): Promise<SyncTiming> {
const cleanText = this.cleanText(text);
// 1. Générer le TTS preview et mesurer sa durée exacte
const ttsResult = await ffmpegService.previewTTS(cleanText, voice);
if (!ttsResult.success || !ttsResult.audioBase64) {
throw new Error('TTS preview failed: ' + (ttsResult.error || 'unknown'));
}
const audioBuffer = Buffer.from(ttsResult.audioBase64, 'base64');
const metadata = await musicMetadata.parseBuffer(audioBuffer, 'audio/mpeg');
const audioDuration = metadata.format.duration || 0;
// 2. Analyser le texte (compte les mots réellement lus par la voix)
const wordCount = this.calculateWordCount(cleanText);
// 3. Calculer le word_duration
const wordDuration = wordCount > 0 ? audioDuration / wordCount : 0.6;
// 4. Validation
const warnings: string[] = [];
const isHealthy = wordDuration >= 0.25 && wordDuration <= 1.5;
if (wordDuration < 0.25) {
warnings.push('Texte trop long : les mots défileront très vite. Envisagez de raccourcir.');
}
if (wordDuration > 1.2) {
warnings.push('Texte très court : affichage lent.');
}
return {
wordDuration,
audioDuration,
wordCount,
punctuationPause: 0,
isHealthy,
warnings,
};
}
private cleanText(text: string): string {
return text
.replace(/#\w+/g, '')
.replace(/https?:\/\/\S+/g, '')
.replace(/[\uD83C-\uD83E][\uDC00-\uDFFF]|[☀-⛿✀-➿]/g, '')
.trim();
}
private calculateWordCount(text: string): number {
const tokens = text.split(/\s+/).filter(w => w.length > 0);
return tokens.filter(w => /[a-zA-Z0-9À-ſ]/.test(w)).length;
}
}
export const ttsSyncService = new TtsSyncService();