mirror of
https://github.com/R0m1k3/Socialflow.git
synced 2026-10-12 01:36:54 +02:00
feat(reels): voix Gemini complète, sous-titres mot à mot et rendu de qualité
Service ffmpeg-api réécrit (ffmpeg-service/app/) : - Appels FFmpeg asynchrones : le service ne se fige plus pendant un rendu - Vidéo récupérée par téléchargement (GET /files/…) au lieu de base64 en JSON - Vraies erreurs HTTP ; échec explicite si la voix demandée est impossible - 30 voix Gemini + ton de lecture (dynamique, chaleureux, promo, calme), clé en en-tête, modèle configurable avec repli - Edge TTS 7 (minutage des mots restauré), secours en voix françaises - Voix traitée : filtre, compression, niveau constant ; musique bouclée et baissée automatiquement sous la voix ; mix final à -14 LUFS - Sous-titres calés mot à mot (Whisper pour Gemini et la voix d'origine, à la place de ffsubsync), style Montserrat, placés hors des boutons Reels - Vidéo : plus de retouche luminosité forcée, scaling lanczos, HDR iPhone converti, BT.709, AAC 48 kHz 192k ; la vidéo s'allonge si la voix dépasse - Grand logo de fin affiché après la voix ; FFmpeg 7.0.2 épinglé, polices et modèle Whisper intégrés à l'image ; tests pytest et ruff Application : - Sélecteur de voix partagé (4 pages) : moteur, 30 voix, ton, écoute - Reel images : minutage réel des mots, interrupteur voix respecté - sync-info ne génère plus de voix à chaque frappe (estimation locale) - Stabilisation désactivée par défaut, route /reels/preview inutilisée retirée - Log « [ReelQueue] Worker démarré » pour vérifier la version déployée Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018Ze4bs7tpF1KGWUk6ZZSZ4
This commit is contained in:
47 files changed
+2206
-2285
No files matched your search
@@ -0,0 +1,185 @@
|
||||
import { useEffect, useRef, useState } from "react";
|
||||
import { Loader2, Play, Square } from "lucide-react";
|
||||
import { Button } from "@/components/ui/button";
|
||||
import { Label } from "@/components/ui/label";
|
||||
import {
|
||||
Select,
|
||||
SelectContent,
|
||||
SelectGroup,
|
||||
SelectItem,
|
||||
SelectLabel,
|
||||
SelectTrigger,
|
||||
SelectValue,
|
||||
} from "@/components/ui/select";
|
||||
import { useToast } from "@/hooks/use-toast";
|
||||
import { apiRequest, getErrorMessage } from "@/lib/queryClient";
|
||||
import {
|
||||
DEFAULT_VOICE,
|
||||
TTS_STYLE_OPTIONS,
|
||||
voicesFor,
|
||||
type TtsEngine,
|
||||
type TtsStyle,
|
||||
} from "@shared/voices";
|
||||
|
||||
export interface VoiceSettings {
|
||||
engine: TtsEngine;
|
||||
voice: string;
|
||||
style: TtsStyle;
|
||||
}
|
||||
|
||||
interface VoicePickerProps {
|
||||
value: VoiceSettings;
|
||||
onChange: (value: VoiceSettings) => void;
|
||||
/** Texte lu par le bouton « Tester la voix ». */
|
||||
sampleText?: string;
|
||||
compact?: boolean;
|
||||
}
|
||||
|
||||
const FALLBACK_SAMPLE = "Découvrez nos nouveautés en magasin, on vous attend !";
|
||||
|
||||
/**
|
||||
* Choix du moteur, de la voix et du ton, avec écoute de l'aperçu.
|
||||
* Partagé par les pages Reel (vidéo et images, bureau et mobile).
|
||||
*/
|
||||
export function VoicePicker({ value, onChange, sampleText, compact = false }: VoicePickerProps) {
|
||||
const { toast } = useToast();
|
||||
const [loading, setLoading] = useState(false);
|
||||
const [playing, setPlaying] = useState(false);
|
||||
const audioRef = useRef<HTMLAudioElement | null>(null);
|
||||
|
||||
useEffect(() => () => audioRef.current?.pause(), []);
|
||||
|
||||
const voices = voicesFor(value.engine);
|
||||
const groups = [
|
||||
{ label: "Voix féminines", items: voices.filter((v) => v.gender === "female") },
|
||||
{ label: "Voix masculines", items: voices.filter((v) => v.gender === "male") },
|
||||
];
|
||||
|
||||
const setEngine = (engine: TtsEngine) => {
|
||||
if (engine !== value.engine) onChange({ ...value, engine, voice: DEFAULT_VOICE[engine] });
|
||||
};
|
||||
|
||||
const stop = () => {
|
||||
audioRef.current?.pause();
|
||||
setPlaying(false);
|
||||
};
|
||||
|
||||
const preview = async () => {
|
||||
if (playing) return stop();
|
||||
setLoading(true);
|
||||
try {
|
||||
const response = await apiRequest("POST", "/api/reels/tts-preview", {
|
||||
text: sampleText?.trim() || FALLBACK_SAMPLE,
|
||||
ttsEngine: value.engine,
|
||||
ttsVoice: value.voice,
|
||||
ttsStyle: value.style,
|
||||
});
|
||||
const data = await response.json();
|
||||
for (const warning of data.warnings ?? []) {
|
||||
toast({ title: "Voix de secours utilisée", description: warning });
|
||||
}
|
||||
const audio = new Audio(`data:audio/mpeg;base64,${data.audioBase64}`);
|
||||
audioRef.current?.pause();
|
||||
audioRef.current = audio;
|
||||
audio.onended = () => setPlaying(false);
|
||||
await audio.play();
|
||||
setPlaying(true);
|
||||
} catch (error) {
|
||||
toast({
|
||||
title: "Impossible de tester la voix",
|
||||
description: getErrorMessage(error, "La voix n'a pas pu être générée."),
|
||||
variant: "destructive",
|
||||
});
|
||||
} finally {
|
||||
setLoading(false);
|
||||
}
|
||||
};
|
||||
|
||||
const labelClass = compact ? "text-xs font-medium" : "text-sm font-medium";
|
||||
|
||||
return (
|
||||
<div className="space-y-3">
|
||||
<div className="flex items-center gap-3">
|
||||
<Label className={`${labelClass} w-14 shrink-0`}>Moteur</Label>
|
||||
<div className="flex gap-2">
|
||||
<Button
|
||||
type="button"
|
||||
size="sm"
|
||||
className={compact ? "h-7 text-xs" : undefined}
|
||||
variant={value.engine === "gemini" ? "default" : "outline"}
|
||||
onClick={() => setEngine("gemini")}
|
||||
>
|
||||
Gemini (naturelle)
|
||||
</Button>
|
||||
<Button
|
||||
type="button"
|
||||
size="sm"
|
||||
className={compact ? "h-7 text-xs" : undefined}
|
||||
variant={value.engine === "edge" ? "default" : "outline"}
|
||||
onClick={() => setEngine("edge")}
|
||||
>
|
||||
Edge (gratuite)
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div className="flex items-center gap-3">
|
||||
<Label className={`${labelClass} w-14 shrink-0`}>Voix</Label>
|
||||
<Select value={value.voice} onValueChange={(voice) => onChange({ ...value, voice })}>
|
||||
<SelectTrigger className={compact ? "h-8 text-xs flex-1" : "flex-1"}>
|
||||
<SelectValue placeholder="Choisir une voix" />
|
||||
</SelectTrigger>
|
||||
<SelectContent className="max-h-72">
|
||||
{groups.map((group) => (
|
||||
<SelectGroup key={group.label}>
|
||||
<SelectLabel>{group.label}</SelectLabel>
|
||||
{group.items.map((voice) => (
|
||||
<SelectItem key={voice.id} value={voice.id}>
|
||||
{voice.label}
|
||||
</SelectItem>
|
||||
))}
|
||||
</SelectGroup>
|
||||
))}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<div className="flex items-center gap-3">
|
||||
<Label className={`${labelClass} w-14 shrink-0`}>Ton</Label>
|
||||
<Select value={value.style} onValueChange={(style) => onChange({ ...value, style: style as TtsStyle })}>
|
||||
<SelectTrigger className={compact ? "h-8 text-xs flex-1" : "flex-1"}>
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{TTS_STYLE_OPTIONS.map((style) => (
|
||||
<SelectItem key={style.id} value={style.id}>
|
||||
{style.label} <span className="text-muted-foreground">— {style.description}</span>
|
||||
</SelectItem>
|
||||
))}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<Button
|
||||
type="button"
|
||||
size="sm"
|
||||
variant="secondary"
|
||||
className={compact ? "w-full h-8 text-xs" : "w-full"}
|
||||
disabled={loading}
|
||||
onClick={(e) => {
|
||||
e.stopPropagation();
|
||||
preview();
|
||||
}}
|
||||
>
|
||||
{loading ? (
|
||||
<Loader2 className="w-3 h-3 mr-2 animate-spin" />
|
||||
) : playing ? (
|
||||
<Square className="w-3 h-3 mr-2" />
|
||||
) : (
|
||||
<Play className="w-3 h-3 mr-2" />
|
||||
)}
|
||||
{loading ? "Génération de la voix…" : playing ? "Arrêter" : "Tester la voix"}
|
||||
</Button>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -16,6 +16,8 @@ import { Switch } from "@/components/ui/switch";
|
||||
import { Label } from "@/components/ui/label";
|
||||
import { Slider } from "@/components/ui/slider";
|
||||
import { useToast } from "@/hooks/use-toast";
|
||||
import { VoicePicker, type VoiceSettings } from "@/components/reels/voice-picker";
|
||||
import { DEFAULT_TTS_STYLE, DEFAULT_VOICE } from "@shared/voices";
|
||||
import { apiRequest, queryClient, handleUnauthorized } from "@/lib/queryClient";
|
||||
import type { SocialPage, Media } from "@shared/schema";
|
||||
import { SiFacebook, SiTiktok } from "react-icons/si";
|
||||
@@ -59,27 +61,17 @@ export default function MobileNewReel() {
|
||||
|
||||
// État TTS
|
||||
const [ttsEnabled, setTtsEnabled] = useState(false);
|
||||
const [ttsEngine, setTtsEngine] = useState<'edge' | 'gemini'>('edge');
|
||||
const [ttsVoice, setTtsVoice] = useState('fr-FR-VivienneMultilingualNeural');
|
||||
|
||||
// Gemini native TTS voices (Charon = homme, Kore = femme)
|
||||
const geminiVoices = [
|
||||
{ label: 'Charon - Voix Homme', value: 'fr-FR-Standard-B' },
|
||||
{ label: 'Kore - Voix Femme', value: 'fr-FR-Standard-A' },
|
||||
];
|
||||
|
||||
// French Edge TTS voices
|
||||
const edgeVoices = [
|
||||
{ label: 'Vivienne (Femme)', value: 'fr-FR-VivienneMultilingualNeural' },
|
||||
{ label: 'Henri (Homme)', value: 'fr-FR-HenriNeural' },
|
||||
{ label: 'Denise (Femme)', value: 'fr-FR-DeniseNeural' },
|
||||
{ label: 'Rémy (Homme)', value: 'fr-FR-RemyMultilingualNeural' },
|
||||
{ label: 'Jenny (Anglaise, Femme)', value: 'en-US-JennyNeural' },
|
||||
];
|
||||
const [voiceSettings, setVoiceSettings] = useState<VoiceSettings>({
|
||||
engine: 'gemini',
|
||||
voice: DEFAULT_VOICE.gemini,
|
||||
style: DEFAULT_TTS_STYLE,
|
||||
});
|
||||
const { engine: ttsEngine, voice: ttsVoice, style: ttsStyle } = voiceSettings;
|
||||
|
||||
// État audio preview
|
||||
const [isPlaying, setIsPlaying] = useState<string | null>(null);
|
||||
const [stabilize, setStabilize] = useState(true); // Activé par défaut pour les Reels
|
||||
// Désactivée par défaut : double le temps de rendu, utile seulement pour une vidéo tremblée
|
||||
const [stabilize, setStabilize] = useState(false);
|
||||
const [enableEndingEffect, setEnableEndingEffect] = useState(true);
|
||||
|
||||
// TTS Sync state
|
||||
@@ -271,6 +263,7 @@ export default function MobileNewReel() {
|
||||
ttsEnabled,
|
||||
ttsEngine,
|
||||
ttsVoice,
|
||||
ttsStyle,
|
||||
enableEndingEffect,
|
||||
});
|
||||
};
|
||||
@@ -492,82 +485,13 @@ export default function MobileNewReel() {
|
||||
<span>TTS — voix activée</span>
|
||||
</div>
|
||||
|
||||
{/* TTS Engine Selector */}
|
||||
<div className="flex items-center gap-2 mt-2">
|
||||
<Label className="text-xs font-medium">Moteur:</Label>
|
||||
<div className="flex gap-1">
|
||||
<Button
|
||||
size="sm"
|
||||
variant={ttsEngine === 'edge' ? 'default' : 'outline'}
|
||||
className="h-7 text-xs px-2"
|
||||
onClick={() => {
|
||||
setTtsEngine('edge');
|
||||
setTtsVoice('fr-FR-VivienneMultilingualNeural');
|
||||
}}
|
||||
>
|
||||
Edge
|
||||
</Button>
|
||||
<Button
|
||||
size="sm"
|
||||
variant={ttsEngine === 'gemini' ? 'default' : 'outline'}
|
||||
className="h-7 text-xs px-2"
|
||||
onClick={() => {
|
||||
setTtsEngine('gemini');
|
||||
setTtsVoice('fr-FR-Standard-B');
|
||||
}}
|
||||
>
|
||||
Gemini
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Voice Selector */}
|
||||
<div className="flex items-center gap-2 mt-2">
|
||||
<Label className="text-xs font-medium shrink-0">Voix:</Label>
|
||||
<Select value={ttsVoice} onValueChange={setTtsVoice}>
|
||||
<SelectTrigger className="h-7 text-xs flex-1">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{ttsEngine === 'edge' ? (
|
||||
edgeVoices.map(v => (
|
||||
<SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>
|
||||
))
|
||||
) : (
|
||||
geminiVoices.map(v => (
|
||||
<SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>
|
||||
))
|
||||
)}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<div className="mt-2">
|
||||
<Button
|
||||
size="sm"
|
||||
variant="secondary"
|
||||
className="w-full h-8 text-xs"
|
||||
onClick={async (e) => {
|
||||
e.stopPropagation();
|
||||
const textToTest = overlayText || "Ceci est un test de voix.";
|
||||
try {
|
||||
const response = await apiRequest('POST', '/api/reels/tts-preview', {
|
||||
text: textToTest,
|
||||
ttsEngine,
|
||||
ttsVoice,
|
||||
});
|
||||
const data = await response.json();
|
||||
if (data.success && data.audioBase64) {
|
||||
const audio = new Audio(`data:audio/mp3;base64,${data.audioBase64}`);
|
||||
audio.play();
|
||||
}
|
||||
} catch (err) {
|
||||
toast({ title: "Erreur", description: "Impossible de lire la voix", variant: "destructive" });
|
||||
}
|
||||
}}
|
||||
>
|
||||
<Play className="w-3 h-3 mr-1" /> Tester la voix
|
||||
</Button>
|
||||
<VoicePicker
|
||||
value={voiceSettings}
|
||||
onChange={setVoiceSettings}
|
||||
sampleText={overlayText}
|
||||
compact
|
||||
/>
|
||||
</div>
|
||||
|
||||
{syncInfo && (
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
import { useState, useRef } from "react";
|
||||
import { useToast } from "@/hooks/use-toast";
|
||||
import { VoicePicker, type VoiceSettings } from "@/components/reels/voice-picker";
|
||||
import { DEFAULT_TTS_STYLE, DEFAULT_VOICE } from "@shared/voices";
|
||||
import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card";
|
||||
import { Button } from "@/components/ui/button";
|
||||
import { Textarea } from "@/components/ui/textarea";
|
||||
@@ -33,23 +35,11 @@ export default function MobileRemotionVideoPage() {
|
||||
const [productInfo, setProductInfo] = useState("");
|
||||
const [generatedVariants, setGeneratedVariants] = useState<any[]>([]);
|
||||
const [ttsEnabled, setTtsEnabled] = useState(true);
|
||||
const [ttsEngine, setTtsEngine] = useState<'edge' | 'gemini'>('edge');
|
||||
const [ttsVoice, setTtsVoice] = useState('fr-FR-VivienneMultilingualNeural');
|
||||
|
||||
// Gemini native TTS voices (Charon = homme, Kore = femme)
|
||||
const geminiVoices = [
|
||||
{ label: 'Charon - Voix Homme', value: 'fr-FR-Standard-B' },
|
||||
{ label: 'Kore - Voix Femme', value: 'fr-FR-Standard-A' },
|
||||
];
|
||||
|
||||
// French Edge TTS voices
|
||||
const edgeVoices = [
|
||||
{ label: 'Vivienne (Femme)', value: 'fr-FR-VivienneMultilingualNeural' },
|
||||
{ label: 'Henri (Homme)', value: 'fr-FR-HenriNeural' },
|
||||
{ label: 'Denise (Femme)', value: 'fr-FR-DeniseNeural' },
|
||||
{ label: 'Rémy (Homme)', value: 'fr-FR-RemyMultilingualNeural' },
|
||||
{ label: 'Jenny (Anglaise, Femme)', value: 'en-US-JennyNeural' },
|
||||
];
|
||||
const [voiceSettings, setVoiceSettings] = useState<VoiceSettings>({
|
||||
engine: 'gemini',
|
||||
voice: DEFAULT_VOICE.gemini,
|
||||
style: DEFAULT_TTS_STYLE,
|
||||
});
|
||||
const [musicFile, setMusicFile] = useState<File | null>(null);
|
||||
const [selectedTrack, setSelectedTrack] = useState<AudioTrack | null>(null);
|
||||
const [musicVolume, setMusicVolume] = useState(0.3);
|
||||
@@ -143,16 +133,6 @@ export default function MobileRemotionVideoPage() {
|
||||
|
||||
const totalSelected = images.length + selectedLibraryImages.length;
|
||||
|
||||
const handleTtsPreview = async () => {
|
||||
const ttsText = stripForTTS(overlayText);
|
||||
if (!ttsText) return;
|
||||
try {
|
||||
const r = await apiRequest('POST', '/api/reels/tts-preview', { text: ttsText, ttsEngine, ttsVoice });
|
||||
const data = await r.json();
|
||||
if (data.success && data.audioBase64) new window.Audio(`data:audio/mp3;base64,${data.audioBase64}`).play();
|
||||
} catch { toast({ title: "Erreur prévisualisation voix", variant: "destructive" }); }
|
||||
};
|
||||
|
||||
const togglePlayPreview = (track: AudioTrack) => {
|
||||
if (!audioRef.current) return;
|
||||
if (isPlaying === track.id) { audioRef.current.pause(); setIsPlaying(null); }
|
||||
@@ -168,8 +148,10 @@ export default function MobileRemotionVideoPage() {
|
||||
images.forEach(img => formData.append("images", img));
|
||||
selectedLibraryImages.forEach(m => formData.append("existingImageUrls", m.originalUrl));
|
||||
if (overlayText) formData.append("overlayText", overlayText);
|
||||
formData.append("ttsEngine", ttsEngine);
|
||||
formData.append("ttsVoice", ttsVoice);
|
||||
formData.append("ttsEnabled", String(ttsEnabled));
|
||||
formData.append("ttsEngine", voiceSettings.engine);
|
||||
formData.append("ttsVoice", voiceSettings.voice);
|
||||
formData.append("ttsStyle", voiceSettings.style);
|
||||
if (selectedPageIds[0]) formData.append("selectedPageId", selectedPageIds[0]);
|
||||
if (musicFile) { formData.append("music", musicFile); formData.append("musicVolume", String(musicVolume)); }
|
||||
else if (selectedTrack) { formData.append("musicTrackUrl", selectedTrack.url); formData.append("musicVolume", String(musicVolume)); }
|
||||
@@ -354,41 +336,7 @@ export default function MobileRemotionVideoPage() {
|
||||
<div className="space-y-2">
|
||||
<p className="text-xs text-muted-foreground">TTS — voix activée</p>
|
||||
|
||||
{/* TTS Engine Selector */}
|
||||
<div className="flex items-center gap-2">
|
||||
<Label className="text-xs font-medium">Moteur:</Label>
|
||||
<div className="flex gap-1">
|
||||
<Button size="sm" variant={ttsEngine === 'edge' ? 'default' : 'outline'} className="h-7 text-xs px-2"
|
||||
onClick={() => { setTtsEngine('edge'); setTtsVoice('fr-FR-VivienneMultilingualNeural'); }}>
|
||||
Edge
|
||||
</Button>
|
||||
<Button size="sm" variant={ttsEngine === 'gemini' ? 'default' : 'outline'} className="h-7 text-xs px-2"
|
||||
onClick={() => { setTtsEngine('gemini'); setTtsVoice('fr-FR-Standard-B'); }}>
|
||||
Gemini
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Voice Selector */}
|
||||
<div className="flex items-center gap-2">
|
||||
<Label className="text-xs font-medium shrink-0">Voix:</Label>
|
||||
<Select value={ttsVoice} onValueChange={setTtsVoice}>
|
||||
<SelectTrigger className="h-7 text-xs flex-1">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{ttsEngine === 'edge' ? (
|
||||
edgeVoices.map(v => <SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>)
|
||||
) : (
|
||||
geminiVoices.map(v => <SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>)
|
||||
)}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<Button size="sm" variant="outline" className="w-full" onClick={handleTtsPreview} disabled={!overlayText}>
|
||||
<Volume2 className="mr-2 w-3 h-3" /> Écouter la voix
|
||||
</Button>
|
||||
<VoicePicker value={voiceSettings} onChange={setVoiceSettings} sampleText={overlayText} compact />
|
||||
</div>
|
||||
)}
|
||||
</CardContent>
|
||||
|
||||
+18
-101
@@ -25,6 +25,8 @@ import {
|
||||
SelectValue,
|
||||
} from "@/components/ui/select";
|
||||
import { useToast } from "@/hooks/use-toast";
|
||||
import { VoicePicker, type VoiceSettings } from "@/components/reels/voice-picker";
|
||||
import { DEFAULT_TTS_STYLE, DEFAULT_VOICE } from "@shared/voices";
|
||||
import { apiRequest, queryClient, handleUnauthorized, getErrorMessage } from "@/lib/queryClient";
|
||||
import type { SocialPage, Media } from "@shared/schema";
|
||||
import { SiFacebook, SiTiktok } from "react-icons/si";
|
||||
@@ -67,7 +69,8 @@ export default function NewReel() {
|
||||
const [musicVolume, setMusicVolume] = useState([25]);
|
||||
const [ttsEnabled, setTtsEnabled] = useState(true);
|
||||
const [drawText, setDrawText] = useState(true);
|
||||
const [stabilize, setStabilize] = useState(true); // default to true
|
||||
// Désactivée par défaut : double le temps de rendu, utile seulement pour une vidéo tremblée
|
||||
const [stabilize, setStabilize] = useState(false);
|
||||
const [enableEndingEffect, setEnableEndingEffect] = useState(true);
|
||||
|
||||
// TTS Sync state
|
||||
@@ -79,24 +82,13 @@ export default function NewReel() {
|
||||
warnings: string[];
|
||||
} | null>(null);
|
||||
|
||||
// TTS Engine & Voice
|
||||
const [ttsEngine, setTtsEngine] = useState<'edge' | 'gemini'>('edge');
|
||||
const [ttsVoice, setTtsVoice] = useState('fr-FR-VivienneMultilingualNeural');
|
||||
|
||||
// Gemini native TTS voices (Charon = homme, Kore = femme)
|
||||
const geminiVoices = [
|
||||
{ label: 'Charon - Voix Homme', value: 'fr-FR-Standard-B' },
|
||||
{ label: 'Kore - Voix Femme', value: 'fr-FR-Standard-A' },
|
||||
];
|
||||
|
||||
// French Edge TTS voices
|
||||
const edgeVoices = [
|
||||
{ label: 'Vivienne (Femme)', value: 'fr-FR-VivienneMultilingualNeural' },
|
||||
{ label: 'Henri (Homme)', value: 'fr-FR-HenriNeural' },
|
||||
{ label: 'Denise (Femme)', value: 'fr-FR-DeniseNeural' },
|
||||
{ label: 'Rémy (Homme)', value: 'fr-FR-RemyMultilingualNeural' },
|
||||
{ label: 'Jenny (Anglaise, Femme)', value: 'en-US-JennyNeural' },
|
||||
];
|
||||
// Voix : moteur, voix et ton de lecture
|
||||
const [voiceSettings, setVoiceSettings] = useState<VoiceSettings>({
|
||||
engine: 'gemini',
|
||||
voice: DEFAULT_VOICE.gemini,
|
||||
style: DEFAULT_TTS_STYLE,
|
||||
});
|
||||
const { engine: ttsEngine, voice: ttsVoice, style: ttsStyle } = voiceSettings;
|
||||
|
||||
// Enable TTS by default on mobile
|
||||
useEffect(() => {
|
||||
@@ -413,6 +405,7 @@ export default function NewReel() {
|
||||
ttsEnabled,
|
||||
ttsEngine,
|
||||
ttsVoice,
|
||||
ttsStyle,
|
||||
drawText,
|
||||
stabilize: stabilize,
|
||||
enableEndingEffect,
|
||||
@@ -819,88 +812,12 @@ export default function NewReel() {
|
||||
<span>TTS — voix activée</span>
|
||||
</div>
|
||||
|
||||
{/* TTS Engine Selector */}
|
||||
<div className="flex items-center gap-4 mt-3">
|
||||
<Label className="text-sm font-medium">Moteur:</Label>
|
||||
<div className="flex gap-2">
|
||||
<Button
|
||||
size="sm"
|
||||
variant={ttsEngine === 'edge' ? 'default' : 'outline'}
|
||||
onClick={() => {
|
||||
setTtsEngine('edge');
|
||||
setTtsVoice('fr-FR-VivienneMultilingualNeural');
|
||||
}}
|
||||
>
|
||||
Edge TTS
|
||||
</Button>
|
||||
<Button
|
||||
size="sm"
|
||||
variant={ttsEngine === 'gemini' ? 'default' : 'outline'}
|
||||
onClick={() => {
|
||||
setTtsEngine('gemini');
|
||||
setTtsVoice('fr-FR-Standard-B');
|
||||
}}
|
||||
>
|
||||
Gemini TTS
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Voice Selector */}
|
||||
<div className="flex items-center gap-3 mt-3">
|
||||
<Label className="text-sm font-medium shrink-0">Voix:</Label>
|
||||
<Select
|
||||
value={ttsVoice}
|
||||
onValueChange={setTtsVoice}
|
||||
>
|
||||
<SelectTrigger className="flex-1">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{ttsEngine === 'edge' ? (
|
||||
edgeVoices.map(v => (
|
||||
<SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>
|
||||
))
|
||||
) : (
|
||||
geminiVoices.map(v => (
|
||||
<SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>
|
||||
))
|
||||
)}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<div className="mt-3 flex gap-2">
|
||||
<Button
|
||||
size="sm"
|
||||
variant="secondary"
|
||||
className="w-full"
|
||||
onClick={async (e) => {
|
||||
e.stopPropagation();
|
||||
const textToTest = overlayText || "Ceci est un test de voix pour votre vidéo.";
|
||||
try {
|
||||
const response = await apiRequest('POST', '/api/reels/tts-preview', {
|
||||
text: textToTest,
|
||||
ttsEngine,
|
||||
ttsVoice,
|
||||
});
|
||||
const data = await response.json();
|
||||
if (data.success && data.audioBase64) {
|
||||
const audio = new Audio(`data:audio/mp3;base64,${data.audioBase64}`);
|
||||
audio.play();
|
||||
}
|
||||
} catch (err) {
|
||||
toast({
|
||||
title: "Erreur",
|
||||
description: "Impossible de tester la voix",
|
||||
variant: "destructive"
|
||||
});
|
||||
}
|
||||
}}
|
||||
>
|
||||
<Play className="w-3 h-3 mr-2" />
|
||||
Tester la voix
|
||||
</Button>
|
||||
<div className="mt-3">
|
||||
<VoicePicker
|
||||
value={voiceSettings}
|
||||
onChange={setVoiceSettings}
|
||||
sampleText={overlayText}
|
||||
/>
|
||||
</div>
|
||||
|
||||
{syncInfo && (
|
||||
|
||||
@@ -2,6 +2,8 @@ import { useState, useRef } from "react";
|
||||
import Sidebar from "@/components/sidebar";
|
||||
import TopBar from "@/components/topbar";
|
||||
import { useToast } from "@/hooks/use-toast";
|
||||
import { VoicePicker, type VoiceSettings } from "@/components/reels/voice-picker";
|
||||
import { DEFAULT_TTS_STYLE, DEFAULT_VOICE } from "@shared/voices";
|
||||
import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card";
|
||||
import { Button } from "@/components/ui/button";
|
||||
import { Textarea } from "@/components/ui/textarea";
|
||||
@@ -34,23 +36,11 @@ export default function RemotionVideoPage() {
|
||||
const [productInfo, setProductInfo] = useState("");
|
||||
const [generatedVariants, setGeneratedVariants] = useState<any[]>([]);
|
||||
const [ttsEnabled, setTtsEnabled] = useState(true);
|
||||
const [ttsEngine, setTtsEngine] = useState<'edge' | 'gemini'>('edge');
|
||||
const [ttsVoice, setTtsVoice] = useState('fr-FR-VivienneMultilingualNeural');
|
||||
|
||||
// Gemini native TTS voices (Charon = homme, Kore = femme)
|
||||
const geminiVoices = [
|
||||
{ label: 'Charon - Voix Homme', value: 'fr-FR-Standard-B' },
|
||||
{ label: 'Kore - Voix Femme', value: 'fr-FR-Standard-A' },
|
||||
];
|
||||
|
||||
// French Edge TTS voices
|
||||
const edgeVoices = [
|
||||
{ label: 'Vivienne (Femme)', value: 'fr-FR-VivienneMultilingualNeural' },
|
||||
{ label: 'Henri (Homme)', value: 'fr-FR-HenriNeural' },
|
||||
{ label: 'Denise (Femme)', value: 'fr-FR-DeniseNeural' },
|
||||
{ label: 'Rémy (Homme)', value: 'fr-FR-RemyMultilingualNeural' },
|
||||
{ label: 'Jenny (Anglaise, Femme)', value: 'en-US-JennyNeural' },
|
||||
];
|
||||
const [voiceSettings, setVoiceSettings] = useState<VoiceSettings>({
|
||||
engine: 'gemini',
|
||||
voice: DEFAULT_VOICE.gemini,
|
||||
style: DEFAULT_TTS_STYLE,
|
||||
});
|
||||
const [musicFile, setMusicFile] = useState<File | null>(null);
|
||||
const [selectedTrack, setSelectedTrack] = useState<AudioTrack | null>(null);
|
||||
const [musicVolume, setMusicVolume] = useState(0.3);
|
||||
@@ -109,16 +99,6 @@ export default function RemotionVideoPage() {
|
||||
});
|
||||
};
|
||||
|
||||
const handleTtsPreview = async () => {
|
||||
const ttsText = overlayText.replace(/#\w+/g, '').replace(/[\uD800-\uDFFF\u2600-\u27BF]/g, '').replace(/\s+/g, ' ').trim();
|
||||
if (!ttsText) return;
|
||||
try {
|
||||
const r = await apiRequest('POST', '/api/reels/tts-preview', { text: ttsText, ttsEngine, ttsVoice });
|
||||
const data = await r.json();
|
||||
if (data.success && data.audioBase64) new window.Audio(`data:audio/mp3;base64,${data.audioBase64}`).play();
|
||||
} catch { toast({ title: "Erreur prévisualisation voix", variant: "destructive" }); }
|
||||
};
|
||||
|
||||
const togglePlayPreview = (track: AudioTrack) => {
|
||||
if (!audioRef.current) return;
|
||||
if (isPlaying === track.id) { audioRef.current.pause(); setIsPlaying(null); }
|
||||
@@ -134,8 +114,10 @@ export default function RemotionVideoPage() {
|
||||
images.forEach(img => formData.append("images", img));
|
||||
selectedLibraryImages.forEach(m => formData.append("existingImageUrls", m.originalUrl));
|
||||
if (overlayText) formData.append("overlayText", overlayText);
|
||||
formData.append("ttsEngine", ttsEngine);
|
||||
formData.append("ttsVoice", ttsVoice);
|
||||
formData.append("ttsEnabled", String(ttsEnabled));
|
||||
formData.append("ttsEngine", voiceSettings.engine);
|
||||
formData.append("ttsVoice", voiceSettings.voice);
|
||||
formData.append("ttsStyle", voiceSettings.style);
|
||||
if (selectedPageIds[0]) formData.append("selectedPageId", selectedPageIds[0]);
|
||||
if (musicFile) { formData.append("music", musicFile); formData.append("musicVolume", String(musicVolume)); }
|
||||
else if (selectedTrack) { formData.append("musicTrackUrl", selectedTrack.url); formData.append("musicVolume", String(musicVolume)); }
|
||||
@@ -294,41 +276,7 @@ export default function RemotionVideoPage() {
|
||||
<div className="space-y-3 p-3 bg-muted/30 rounded-lg border">
|
||||
<p className="text-sm text-muted-foreground">TTS — voix activée</p>
|
||||
|
||||
{/* TTS Engine Selector */}
|
||||
<div className="flex items-center gap-2">
|
||||
<Label className="text-xs font-medium">Moteur:</Label>
|
||||
<div className="flex gap-1">
|
||||
<Button size="sm" variant={ttsEngine === 'edge' ? 'default' : 'outline'} className="h-7 text-xs"
|
||||
onClick={() => { setTtsEngine('edge'); setTtsVoice('fr-FR-VivienneMultilingualNeural'); }}>
|
||||
Edge
|
||||
</Button>
|
||||
<Button size="sm" variant={ttsEngine === 'gemini' ? 'default' : 'outline'} className="h-7 text-xs"
|
||||
onClick={() => { setTtsEngine('gemini'); setTtsVoice('fr-FR-Standard-B'); }}>
|
||||
Gemini
|
||||
</Button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
{/* Voice Selector */}
|
||||
<div className="flex items-center gap-2">
|
||||
<Label className="text-xs font-medium shrink-0">Voix:</Label>
|
||||
<Select value={ttsVoice} onValueChange={setTtsVoice}>
|
||||
<SelectTrigger className="h-7 text-xs flex-1">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{ttsEngine === 'edge' ? (
|
||||
edgeVoices.map(v => <SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>)
|
||||
) : (
|
||||
geminiVoices.map(v => <SelectItem key={v.value} value={v.value}>{v.label}</SelectItem>)
|
||||
)}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</div>
|
||||
|
||||
<Button size="sm" variant="outline" className="w-full" onClick={handleTtsPreview} disabled={!overlayText}>
|
||||
<Volume2 className="mr-2 w-3 h-3" /> Écouter la voix
|
||||
</Button>
|
||||
<VoicePicker value={voiceSettings} onChange={setVoiceSettings} sampleText={overlayText} />
|
||||
</div>
|
||||
)}
|
||||
</CardContent>
|
||||
|
||||
Reference in new issue
Block a user