Michael/Socialflow
1
0 Fork 0
mirror of https://github.com/R0m1k3/Socialflow.git synced 2026-10-11 17:26:45 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add Google Gemini TTS as alternative to Edge TTS

Browse Source 
- Store Gemini API key globally in appConfig (single key for all users)
- Add /api/settings/gemini GET/POST/DELETE routes for API key management
- Backend: add tts_engine parameter ("edge" or "gemini") to FFmpeg service
- Backend: add generate_tts_gemini() using Google Cloud TTS REST API
- Frontend: Settings page shows Google Gemini API key input card
- Frontend: new-reel, mobile/new-reel, remotion-video, mobile/remotion-video
  pages now have Edge/Gemini engine toggle and French voice selector
- Fix tts-preview route to extract ttsVoice from req.body instead of
  undefined voice variable
This commit is contained in:
Michael committed 2026-05-19 12:17:42 +02:00
1 parent 59bc56aedc
commit 72b13b3e42
12 files changed
+605 -29
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

client/src/pages/mobile/new-reel.tsx
+82 -3
View File
@@ -58,6 +58,29 @@ 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');
// French Gemini voices
const geminiVoices = [
{ label: 'Français - Standard A (Femme)', value: 'fr-FR-Standard-A' },
{ label: 'Français - Standard B (Homme)', value: 'fr-FR-Standard-B' },
{ label: 'Français - Standard C (Femme)', value: 'fr-FR-Standard-C' },
{ label: 'Français - Standard D (Homme)', value: 'fr-FR-Standard-D' },
{ label: 'Français - Wavenet A (Femme)', value: 'fr-FR-Wavenet-A' },
{ label: 'Français - Wavenet B (Homme)', value: 'fr-FR-Wavenet-B' },
{ label: 'Français - Wavenet C (Femme)', value: 'fr-FR-Wavenet-C' },
{ label: 'Français - Wavenet D (Homme)', value: 'fr-FR-Wavenet-D' },
];
// 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' },
];
// État audio preview
const [isPlaying, setIsPlaying] = useState<string | null>(null);
@@ -82,14 +105,15 @@ export default function MobileNewReel() {
const timer = setTimeout(() => {
apiRequest('POST', '/api/reels/sync-info', {
text: overlayText,
voice: "fr-FR-VivienneMultilingualNeural",
ttsEngine,
ttsVoice,
})
.then(r => r.json())
.then(data => setSyncInfo(data))
.catch(() => setSyncInfo(null));
}, 800);
return () => clearTimeout(timer);
}, [overlayText, ttsEnabled]);
}, [overlayText, ttsEnabled, ttsEngine, ttsVoice]);
const { data: pages = [] } = useQuery<SocialPage[]>({
@@ -230,6 +254,8 @@ export default function MobileNewReel() {
stabilize: stabilize,
drawText: true,
ttsEnabled,
ttsEngine,
ttsVoice,
enableEndingEffect,
});
};
@@ -450,7 +476,58 @@ export default function MobileNewReel() {
<Mic className="w-4 h-4" />
<span>TTS — voix activée</span>
</div>
<div className="mt-3">
{/* 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-A');
}}
>
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"
@@ -461,6 +538,8 @@ export default function MobileNewReel() {
try {
const response = await apiRequest('POST', '/api/reels/tts-preview', {
text: textToTest,
ttsEngine,
ttsVoice,
});
const data = await response.json();
if (data.success && data.audioBase64) {
client/src/pages/mobile/remotion-video.tsx
+57 -1
View File
@@ -31,6 +31,29 @@ 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');
// French Gemini voices
const geminiVoices = [
{ label: 'Français - Standard A (Femme)', value: 'fr-FR-Standard-A' },
{ label: 'Français - Standard B (Homme)', value: 'fr-FR-Standard-B' },
{ label: 'Français - Standard C (Femme)', value: 'fr-FR-Standard-C' },
{ label: 'Français - Standard D (Homme)', value: 'fr-FR-Standard-D' },
{ label: 'Français - Wavenet A (Femme)', value: 'fr-FR-Wavenet-A' },
{ label: 'Français - Wavenet B (Homme)', value: 'fr-FR-Wavenet-B' },
{ label: 'Français - Wavenet C (Femme)', value: 'fr-FR-Wavenet-C' },
{ label: 'Français - Wavenet D (Homme)', value: 'fr-FR-Wavenet-D' },
];
// 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 [musicFile, setMusicFile] = useState<File | null>(null);
const [selectedTrack, setSelectedTrack] = useState<AudioTrack | null>(null);
const [musicVolume, setMusicVolume] = useState(0.3);
@@ -111,7 +134,7 @@ export default function MobileRemotionVideoPage() {
const ttsText = stripForTTS(overlayText);
if (!ttsText) return;
try {
const r = await apiRequest('POST', '/api/reels/tts-preview', { text: ttsText });
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" }); }
@@ -312,6 +335,39 @@ export default function MobileRemotionVideoPage() {
{ttsEnabled && (
<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-A'); }}>
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>
client/src/pages/new-reel.tsx
+83 -3
View File
@@ -78,6 +78,31 @@ 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');
// French Gemini voices
const geminiVoices = [
{ label: 'Français - Standard A (Femme)', value: 'fr-FR-Standard-A' },
{ label: 'Français - Standard B (Homme)', value: 'fr-FR-Standard-B' },
{ label: 'Français - Standard C (Femme)', value: 'fr-FR-Standard-C' },
{ label: 'Français - Standard D (Homme)', value: 'fr-FR-Standard-D' },
{ label: 'Français - Wavenet A (Femme)', value: 'fr-FR-Wavenet-A' },
{ label: 'Français - Wavenet B (Homme)', value: 'fr-FR-Wavenet-B' },
{ label: 'Français - Wavenet C (Femme)', value: 'fr-FR-Wavenet-C' },
{ label: 'Français - Wavenet D (Homme)', value: 'fr-FR-Wavenet-D' },
];
// 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' },
];
// Enable TTS by default on mobile
useEffect(() => {
const isMobile = window.innerWidth < 768;
@@ -86,7 +111,7 @@ export default function NewReel() {
}
}, []);
// Auto-calculate TTS sync when text changes (edge_tts fallback)
// Auto-calculate TTS sync when text changes
useEffect(() => {
if (!ttsEnabled || !overlayText.trim()) {
setSyncInfo(null);
@@ -95,14 +120,14 @@ export default function NewReel() {
const timer = setTimeout(() => {
apiRequest('POST', '/api/reels/sync-info', {
text: overlayText,
voice: "fr-FR-VivienneMultilingualNeural",
voice: ttsVoice,
})
.then(r => r.json())
.then(data => setSyncInfo(data))
.catch(() => setSyncInfo(null));
}, 800);
return () => clearTimeout(timer);
}, [overlayText, ttsEnabled]);
}, [overlayText, ttsEnabled, ttsVoice]);
// État audio preview
@@ -360,6 +385,8 @@ export default function NewReel() {
scheduledFor: scheduledDate?.toISOString(),
musicVolume: musicVolume[0] / 100,
ttsEnabled,
ttsEngine,
ttsVoice,
drawText,
stabilize: stabilize,
enableEndingEffect,
@@ -765,6 +792,57 @@ 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-A');
}}
>
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"
@@ -776,6 +854,8 @@ export default function NewReel() {
try {
const response = await apiRequest('POST', '/api/reels/tts-preview', {
text: textToTest,
ttsEngine,
ttsVoice,
});
const data = await response.json();
if (data.success && data.audioBase64) {
client/src/pages/remotion-video.tsx
+57 -1
View File
@@ -32,6 +32,29 @@ 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');
// French Gemini voices
const geminiVoices = [
{ label: 'Français - Standard A (Femme)', value: 'fr-FR-Standard-A' },
{ label: 'Français - Standard B (Homme)', value: 'fr-FR-Standard-B' },
{ label: 'Français - Standard C (Femme)', value: 'fr-FR-Standard-C' },
{ label: 'Français - Standard D (Homme)', value: 'fr-FR-Standard-D' },
{ label: 'Français - Wavenet A (Femme)', value: 'fr-FR-Wavenet-A' },
{ label: 'Français - Wavenet B (Homme)', value: 'fr-FR-Wavenet-B' },
{ label: 'Français - Wavenet C (Femme)', value: 'fr-FR-Wavenet-C' },
{ label: 'Français - Wavenet D (Homme)', value: 'fr-FR-Wavenet-D' },
];
// 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 [musicFile, setMusicFile] = useState<File | null>(null);
const [selectedTrack, setSelectedTrack] = useState<AudioTrack | null>(null);
const [musicVolume, setMusicVolume] = useState(0.3);
@@ -78,7 +101,7 @@ export default function RemotionVideoPage() {
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 });
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" }); }
@@ -253,6 +276,39 @@ export default function RemotionVideoPage() {
{ttsEnabled && (
<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-A'); }}>
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>
client/src/pages/settings.tsx
+84
View File
@@ -30,6 +30,7 @@ export default function Settings() {
const [ffmpegApiUrl, setFfmpegApiUrl] = useState("");
const [ffmpegApiKey, setFfmpegApiKey] = useState("");
const [externalApiKey, setExternalApiKey] = useState("");
const [geminiApiKey, setGeminiApiKey] = useState("");
const { toast } = useToast();
const { data: session } = useQuery<{ id: string; username: string; role: string }>({
@@ -60,6 +61,11 @@ export default function Settings() {
enabled: isAdmin,
});
const { data: geminiConfig } = useQuery({
queryKey: ['/api/settings/gemini'],
enabled: isAdmin,
});
useEffect(() => {
if (cloudinaryConfig) {
setCloudName((cloudinaryConfig as any).cloudName || "");
@@ -86,9 +92,16 @@ export default function Settings() {
}
}, [ffmpegConfig]);
useEffect(() => {
if (geminiConfig) {
// Don't pre-fill - user must enter key manually
}
}, [geminiConfig]);
// Vérifier si une config OpenRouter existe déjà
const hasExistingConfig = !!openrouterConfig;
const hasExistingFfmpegConfig = !!ffmpegConfig;
const hasExistingGeminiConfig = !!(geminiConfig as any)?.configured;
const saveCloudinaryMutation = useMutation({
mutationFn: () => {
@@ -157,6 +170,31 @@ export default function Settings() {
},
});
const saveGeminiMutation = useMutation({
mutationFn: () => {
const payload: any = {};
if (geminiApiKey && geminiApiKey.trim() !== "") {
payload.apiKey = geminiApiKey;
}
return apiRequest('POST', '/api/settings/gemini', payload);
},
onSuccess: () => {
queryClient.invalidateQueries({ queryKey: ['/api/settings/gemini'] });
toast({
title: "Configuration sauvegardée",
description: "Votre clé API Gemini a été enregistrée",
});
setGeminiApiKey("");
},
onError: () => {
toast({
title: "Erreur",
description: "Impossible de sauvegarder la configuration Gemini",
variant: "destructive",
});
},
});
const uploadLogoMutation = useMutation({
mutationFn: async (file: File) => {
const formData = new FormData();
@@ -521,6 +559,52 @@ export default function Settings() {
</CardContent>
</Card>
{/* Google Gemini TTS */}
{isAdmin && (
<Card className="rounded-2xl border-border/50 shadow-lg">
<CardHeader className="p-6">
<CardTitle className="flex items-center gap-2">
<Mic className="w-5 h-5" />
Google Gemini TTS
</CardTitle>
<CardDescription>
Configurez votre clé API Google pour utiliser Gemini TTS dans les Reels
</CardDescription>
</CardHeader>
<CardContent className="space-y-4">
<div className="space-y-2">
<Label htmlFor="geminiApiKey">Clé API Google Gemini</Label>
<Input
id="geminiApiKey"
type="password"
value={geminiApiKey}
onChange={(e) => setGeminiApiKey(e.target.value)}
placeholder={hasExistingGeminiConfig ? "••••••••••••••••" : "AIza..."}
data-testid="input-gemini-api-key"
/>
<p className="text-xs text-muted-foreground">
{hasExistingGeminiConfig ? (
<span className="text-green-600 dark:text-green-400">✓ Clé API configurée</span>
) : (
"Obtenez une clé API sur console.cloud.google.com → APIs & Services → Credentials"
)}
</p>
</div>
<Button
onClick={() => saveGeminiMutation.mutate()}
disabled={
saveGeminiMutation.isPending ||
(!hasExistingGeminiConfig && !geminiApiKey)
}
data-testid="button-save-gemini"
className="w-full"
>
{saveGeminiMutation.isPending ? "Enregistrement..." : "Enregistrer Gemini TTS"}
</Button>
</CardContent>
</Card>
)}
{isAdmin && (
<Card className="rounded-2xl border-border/50 shadow-lg">
ffmpeg-service/main.py
+159 -15
View File
@@ -159,6 +159,8 @@ class ReelRequest(BaseModel):
music_volume: float = 0.25
tts_enabled: bool = False
tts_voice: str = "fr-FR-VivienneMultilingualNeural"
tts_engine: str = "edge" # "edge" or "gemini"
gemini_api_key: Optional[str] = None # Google Cloud API key for Gemini TTS
draw_text: bool = True
stabilize: bool = False # Stabilisation vidéo via vidstab
enable_ending_effect: bool = True
@@ -192,6 +194,123 @@ def clean_text_for_tts(text: str) -> str:
return " ".join(text.split())
async def generate_tts_gemini(
text: str,
voice: str,
api_key: str,
audio_path: Path,
ass_path: Path,
display_text: Optional[str] = None,
delay: float = 0.0,
):
"""Generate TTS audio using Google Cloud TTS API with word-level synchronized subtitles."""
try:
import httpx
print(f"\ud83d\udd0a Gemini TTS request: voice={voice}, text_len={len(text)}")
# Google Cloud TTS REST API
url = f"https://texttospeech.googleapis.com/v1/text:synthesize?key={api_key}"
# Map voice name to Google Cloud TTS voice settings
# Gemini/GCloud uses format: languageCode-Name-Sex (e.g., "fr-FR-Standard-A")
# voice parameter is already in format: fr-FR-Standard-A or fr-FR-Wavenet-A
voice_name = voice
# Determine gender from voice name
is_male = any(name in voice for name in ["B", "D", "M"]) # B, D are typically male
payload = {
"input": {"text": text},
"voice": {
"languageCode": voice.rsplit("-", 2)[0] if "-" in voice else "fr-FR",
"name": voice,
},
"audioConfig": {
"audioEncoding": "MP3",
"speakingRate": 1.0,
"pitch": 0.0,
},
"enableWordTimeOffsets": True,
}
async with httpx.AsyncClient(timeout=60.0) as client:
response = await client.post(url, json=payload)
response.raise_for_status()
data = response.json()
audio_content = base64.b64decode(data["audioContent"])
with open(audio_path, "wb") as f:
f.write(audio_content)
print(f"\u2705 Gemini TTS audio saved: {audio_path.stat().st_size} bytes")
# Parse word time offsets from response
word_boundaries = []
if "wordTimeOffsets" in data.get("timepoints", []):
for tp in data["timepoints"]:
if "word" in tp and "startTime" in tp and "endTime" in tp:
# Parse Google duration format: "0s" or "0.123s"
start_str = tp["startTime"].rstrip("s")
end_str = tp["endTime"].rstrip("s")
try:
start_sec = float(start_str)
end_sec = float(end_str)
word_boundaries.append({
"text": tp["word"],
"offset": start_sec,
"duration": end_sec - start_sec,
})
except ValueError:
pass
print(f"\ud83d\udccd Captured {len(word_boundaries)} word boundaries from Gemini")
# Measure total audio duration
audio_duration = None
try:
duration_cmd = [
"ffprobe",
"-v", "error",
"-show_entries", "format=duration",
"-of", "default=noprint_wrappers=1:nokey=1",
str(audio_path),
]
dur_proc = subprocess.run(duration_cmd, stdout=subprocess.PIPE, text=True)
audio_duration = float(dur_proc.stdout.strip())
print(f"\u23f1\ufe0f TTS Audio Duration: {audio_duration:.2f}s")
except Exception as e:
print(f"\u26a0\ufe0f Could not measure TTS duration: {e}")
text_to_display = display_text if display_text else text
if len(word_boundaries) == 0:
print("\u26a0\ufe0f No word boundaries from Gemini, falling back to ffsubsync")
unsynced_srt_path = audio_path.with_suffix(".unsynced.srt")
synced_srt_path = audio_path.with_suffix(".synced.srt")
generate_unsynced_srt(text_to_display, unsynced_srt_path, total_duration=audio_duration)
run_ffsubsync(audio_path, unsynced_srt_path, synced_srt_path)
convert_srt_to_ass(synced_srt_path, ass_path, font_size=65, delay=delay)
print(f"\u2705 TTS synchronisation completed with ffsubsync fallback")
return
print("\ud83c\udfaf Using precise word-boundary timing from Gemini TTS")
generate_ass_from_word_boundaries(
word_boundaries,
text_to_display,
ass_path,
font_size=65,
total_duration=audio_duration,
delay=delay,
)
print(f"\u2705 TTS synchronisation completed with word-boundary timing")
return
except Exception as e:
print(f"\u274c Gemini TTS failed: {e}")
raise
async def generate_tts_with_subs(
text: str,
voice: str,
@@ -807,14 +926,27 @@ async def process_reel(request: ReelRequest, x_api_key: str = Header(None)):
if tts_clean_text:
print(f"🔊 Generating TTS audio to: {tts_audio_path}")
await generate_tts_with_subs(
tts_clean_text,
voice,
tts_audio_path,
tts_ass_path,
display_text=clean_text_for_display(request.text),
delay=2.0,
)
engine = request.tts_engine or "edge"
if engine == "gemini" and request.gemini_api_key:
await generate_tts_gemini(
tts_clean_text,
voice,
request.gemini_api_key,
tts_audio_path,
tts_ass_path,
display_text=clean_text_for_display(request.text),
delay=2.0,
)
else:
await generate_tts_with_subs(
tts_clean_text,
voice,
tts_audio_path,
tts_ass_path,
display_text=clean_text_for_display(request.text),
delay=2.0,
)
# Verify files were created
if tts_audio_path.exists() and tts_audio_path.stat().st_size > 0:
@@ -1191,13 +1323,25 @@ async def preview_tts(request: ReelRequest, x_api_key: str = Header(None)):
elif not voice or "Neural" not in voice:
voice = "fr-FR-VivienneMultilingualNeural"
await generate_tts_with_subs(
clean_text,
voice,
tts_audio_path,
tts_srt_path,
display_text=clean_text_for_display(request.text),
)
engine = request.tts_engine or "edge"
if engine == "gemini" and request.gemini_api_key:
await generate_tts_gemini(
clean_text,
voice,
request.gemini_api_key,
tts_audio_path,
tts_srt_path,
display_text=clean_text_for_display(request.text),
)
else:
await generate_tts_with_subs(
clean_text,
voice,
tts_audio_path,
tts_srt_path,
display_text=clean_text_for_display(request.text),
)
if not tts_audio_path.exists():
raise Exception("TTS generation failed (file missing)")
ffmpeg-service/requirements.txt
+1
View File
@@ -6,3 +6,4 @@ pydantic==2.6.0
edge-tts==6.1.12
emoji
ffsubsync==0.4.26
httpx>=0.25.0
server/routes.ts
+35
View File
@@ -420,6 +420,41 @@ export async function registerRoutes(app: Express): Promise<Server> {
}
});
// Google Gemini API Key (TTS)
app.get("/api/settings/gemini", requireAdmin, async (req, res) => {
try {
const config = await storage.getAppConfig();
res.json({ configured: !!(config?.geminiApiKey) });
} catch (error) {
console.error("Error fetching Gemini config:", error);
res.status(500).json({ error: "Erreur lors de la récupération de la configuration" });
}
});
app.post("/api/settings/gemini", requireAdmin, async (req, res) => {
try {
const { apiKey } = req.body;
if (!apiKey || typeof apiKey !== "string" || apiKey.trim() === "") {
return res.status(400).json({ error: "La clé API est requise" });
}
await storage.upsertAppConfig({ geminiApiKey: apiKey.trim() });
res.json({ success: true, configured: true });
} catch (error) {
console.error("Error saving Gemini config:", error);
res.status(500).json({ error: "Erreur lors de la sauvegarde de la configuration" });
}
});
app.delete("/api/settings/gemini", requireAdmin, async (req, res) => {
try {
await storage.upsertAppConfig({ geminiApiKey: null });
res.json({ success: true, configured: false });
} catch (error) {
console.error("Error deleting Gemini config:", error);
res.status(500).json({ error: "Erreur lors de la suppression de la clé" });
}
});
// Analytics Routes
app.use("/api/analytics", requireAuth, analyticsRouter);
server/routes/reels.ts
+29 -3
View File
@@ -270,6 +270,8 @@ reelsRouter.post('/reels/preview', async (req: Request, res: Response) => {
musicUrl,
overlayText,
ttsEnabled,
ttsVoice,
ttsEngine,
wordDuration = 0.6,
fontSize = 64,
musicVolume = 0.25,
@@ -318,6 +320,13 @@ reelsRouter.post('/reels/preview', async (req: Request, res: Response) => {
console.error('Error fetching watermark configuration', e);
}
// Get Gemini API key if using Gemini TTS
let geminiApiKey: string | undefined = undefined;
if (ttsEngine === "gemini") {
const appCfg = await storage.getAppConfig();
geminiApiKey = appCfg?.geminiApiKey ?? undefined;
}
const finalWordDuration = wordDuration;
// Traiter la vidéo via FFmpeg
@@ -326,6 +335,8 @@ reelsRouter.post('/reels/preview', async (req: Request, res: Response) => {
musicUrl: finalMusicUrl,
ttsEnabled,
ttsVoice,
ttsEngine,
geminiApiKey,
wordDuration: finalWordDuration,
fontSize,
musicVolume,
@@ -358,13 +369,13 @@ reelsRouter.post('/reels/preview', async (req: Request, res: Response) => {
reelsRouter.post('/reels/tts-preview', async (req: Request, res: Response) => {
try {
const user = req.user as User;
const { text } = req.body;
const { text, ttsVoice, ttsEngine } = req.body;
if (!text) {
return res.status(400).json({ error: 'Texte requis' });
}
const result = await ffmpegService.previewTTS(text, voice);
const result = await ffmpegService.previewTTS(text, ttsVoice, ttsEngine, undefined);
if (!result.success) {
return res.status(500).json({ error: result.error || 'Erreur de génération TTS' });
@@ -455,6 +466,8 @@ async function processReelBackground(
overlayText?: string;
description?: string;
ttsEnabled?: boolean;
ttsVoice?: string;
ttsEngine?: string;
pageIds: string[];
scheduledFor?: string;
wordDuration?: number;
@@ -473,6 +486,8 @@ async function processReelBackground(
overlayText,
description,
ttsEnabled,
ttsVoice,
ttsEngine,
pageIds,
scheduledFor,
wordDuration,
@@ -541,15 +556,24 @@ async function processReelBackground(
console.error('Error fetching watermark configuration', e);
}
// Get Gemini API key if using Gemini TTS
let geminiApiKey: string | undefined = undefined;
if (ttsEngine === "gemini") {
const appCfg = await storage.getAppConfig();
geminiApiKey = appCfg?.geminiApiKey ?? undefined;
}
const finalWordDuration = wordDuration ?? 0.6;
console.log('🔊 [Background] TTS config:', { ttsEnabled, ttsVoice });
console.log('🔊 [Background] TTS config:', { ttsEnabled, ttsVoice, ttsEngine });
const ffmpegResult = await ffmpegService.processReelFromUrl(resolveInternalUrl(media.originalUrl), {
text: overlayText,
musicUrl: finalMusicUrl,
ttsEnabled,
ttsVoice,
ttsEngine,
geminiApiKey,
wordDuration: finalWordDuration,
fontSize,
musicVolume,
@@ -713,6 +737,8 @@ reelsRouter.post('/reels', async (req: Request, res: Response) => {
overlayText,
description,
ttsEnabled,
ttsVoice,
ttsEngine,
pageIds,
scheduledFor,
wordDuration = 0.6,
server/services/ffmpeg.ts
+15 -1
View File
@@ -13,6 +13,8 @@ interface FFmpegReelRequest {
music_url?: string; // OU URL directe de la musique
tts_enabled?: boolean; // Activation du TTS
tts_voice?: string; // Voix TTS (ex: fr-FR-VivienneNeural)
tts_engine?: string; // Moteur TTS: "edge" ou "gemini"
gemini_api_key?: string; // Clé API Google Gemini pour TTS
word_duration?: number; // Durée par mot (default: 0.6s)
font_size?: number; // Taille police (default: 24)
music_volume?: number; // Volume musique (default: 0.25)
@@ -72,6 +74,8 @@ export class FFmpegService {
musicUrl?: string;
ttsEnabled?: boolean;
ttsVoice?: string;
ttsEngine?: string;
geminiApiKey?: string;
wordDuration?: number;
fontSize?: number;
musicVolume?: number;
@@ -91,6 +95,8 @@ export class FFmpegService {
music_url: options.musicUrl,
tts_enabled: options.ttsEnabled,
tts_voice: options.ttsVoice,
tts_engine: options.ttsEngine,
gemini_api_key: options.geminiApiKey,
word_duration: options.wordDuration ?? 0.6,
font_size: options.fontSize ?? 64,
music_volume: options.musicVolume ?? 0.25,
@@ -173,6 +179,8 @@ export class FFmpegService {
musicUrl?: string;
ttsEnabled?: boolean;
ttsVoice?: string;
ttsEngine?: string;
geminiApiKey?: string;
wordDuration?: number;
fontSize?: number;
musicVolume?: number;
@@ -192,6 +200,8 @@ export class FFmpegService {
music_url: options.musicUrl,
tts_enabled: options.ttsEnabled,
tts_voice: options.ttsVoice,
tts_engine: options.ttsEngine,
gemini_api_key: options.geminiApiKey,
word_duration: options.wordDuration ?? 0.6,
font_size: options.fontSize ?? 64,
music_volume: options.musicVolume ?? 0.25,
@@ -290,7 +300,9 @@ export class FFmpegService {
}
async previewTTS(
text: string,
ttsVoice?: string
ttsVoice?: string,
ttsEngine?: string,
geminiApiKey?: string
): Promise<{ success: boolean; audioBase64?: string; error?: string }> {
const config = this.ensureConfigured();
@@ -305,6 +317,8 @@ export class FFmpegService {
text,
tts_enabled: true,
tts_voice: ttsVoice,
tts_engine: ttsEngine,
gemini_api_key: geminiApiKey,
}),
});
server/storage.ts
+2 -2
View File
@@ -124,7 +124,7 @@ export interface IStorage {
// App Config
getAppConfig(): Promise<AppConfig | undefined>;
upsertAppConfig(data: Partial<Pick<AppConfig, 'externalApiKey'>>): Promise<AppConfig>;
upsertAppConfig(data: Partial<Pick<AppConfig, 'externalApiKey' | 'geminiApiKey'>>): Promise<AppConfig>;
}
export class DatabaseStorage implements IStorage {
@@ -571,7 +571,7 @@ export class DatabaseStorage implements IStorage {
return config || undefined;
}
async upsertAppConfig(data: Partial<Pick<AppConfig, 'externalApiKey'>>): Promise<AppConfig> {
async upsertAppConfig(data: Partial<Pick<AppConfig, 'externalApiKey' | 'geminiApiKey'>>): Promise<AppConfig> {
const existing = await this.getAppConfig();
if (existing) {
const [updated] = await db.update(appConfig)
shared/schema.ts
+1
View File
@@ -209,6 +209,7 @@ export const musicFavorites = pgTable("music_favorites", {
export const appConfig = pgTable("app_config", {
id: varchar("id").primaryKey().default(sql`gen_random_uuid()`),
externalApiKey: text("external_api_key"),
geminiApiKey: text("gemini_api_key"),
createdAt: timestamp("created_at").defaultNow(),
updatedAt: timestamp("updated_at").defaultNow(),
});