Cloner de la voix d'IA
Cloner n'importe quelle voix à partir d'un court clip audio. Télécharger 3-10 secondes de parole, taper votre texte, et générer de l'audio dans la même voix.
Clone : fournir un clip de référence de 3-10s. Préréglage : choisir à partir de voix multilingues groupées.
Télécharger l'audio de référence vocale
MP3, WAV, M4A, FLAC
Les préréglages VibeVoice couvrent l'anglais, l'allemand, le français, le japonais, le coréen, le polonais, le portugais, l'espagnol, l'italien, le néerlandais.
Max 500 caractères
0/500
Utilisation d'un crédit par génération
Production de l'audio
Ce son est généré par l'IA. Le fichier WAV téléchargé intègre une divulgation lisible par machine (RIFF INFO chunk) par l'article 50 de la loi sur l'IA de l'UE. Ne présentez pas cet audio comme un enregistrement d'une personne réelle sans consentement.
Politique de l'IA
Comment ça marche
1
Référence de chargement
Fournissez 3-10 secondes de discours clair de la voix que vous voulez cloner.
2
AI analyse la voix
F5-TTS extrait les caractéristiques de la voix : ton, pitch, style de parole, accent.
3
Générer un discours
Votre texte est parlé dans la voix clonée. Téléchargez le résultat comme WAV.
Le clonage vocal est réservé à un usage personnel et autorisé. Ne pas cloner des voix sans le consentement de l'orateur.
Questions fréquemment posées
voice cloning runs in your browser: paste a URL, upload a file, or record from your mic. STT.ai picks the AI model and returns the transcript in under 5 minutes. Export as TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes — every visitor gets 600 free minutes/month on STT.ai, usable for voice cloning the same as any other workflow. Paid plans starting at $5/month unlock longer files, private transcripts, and priority queueing.
voice cloning runs on the same AI models as the rest of STT.ai — our best models reach 95-97% accuracy on clean speech (3-5% Word Error Rate on benchmarks). Switch models on the fly if the first pass is below your target.
voice cloning can run on any of STT.ai's 10+ models — STT.ai Enhanced (most accurate), Whisper Large V3 (99 languages), NVIDIA Canary (#1 WER on supported langs), Whisper Turbo (fast), Moonshine (lightweight), and more.
Yes. Every transcript exports as SRT or VTT — works with YouTube, Vimeo, TikTok, VLC, and every major video player. The burn-subtitles tool overlays them onto video as hardsubs.
Yes. Speaker diarization automatically labels each voice (Speaker 1, Speaker 2, ...) and you can rename them in the built-in editor. Works across all models and languages.
Most voice cloning jobs finish in under 5 minutes. A 1-hour audio file typically completes in 2-3 minutes with our fastest models. Speed depends on chosen model and current GPU load.
voice cloning accepts 20+ formats — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and more. Output to TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes. Audio files submitted to voice cloning are processed and deleted by default. Pro plans add client-side encryption — even if STT.ai's database is breached, your transcripts are unreadable without your key. Data is never used for model training without explicit opt-in.
Yes. STT.ai offers a REST API with Python and Node.js SDKs, plus an MCP server for Claude and Cursor — all usable for voice cloning workflows. Free API tier includes 100 minutes/month.
Yes. Every transcript opens in the built-in editor where you can correct words, rename speakers, adjust timestamps, and add notes. All changes save automatically.
Every transcript gets a unique shareable URL. Export to DOCX or PDF for email. Pro plans add password-protected and permanent links — useful for client work.
STT.ai handles 1,300+ platforms including YouTube, Vimeo, TikTok, SoundCloud, Zoom, Google Meet, podcast hosts, and more. URL transcription works with publicly-available content only — DRM-protected sources can't be transcribed.