Tous les modèles
génération audio
Clone Voice
Clone Voice uses Alibaba’s Qwen3-TTS 1.7B Base model to synthesize multilingual speech from a consented reference recording. It supports a short reference, optional matching transcript, language selection, playback speed, and higher-similarity in-context mode, while Gobostock keeps every saved clone private and tied to the engine that created it.
The audio tool calculates the final credit quote from the selected operation and output settings. Le devis affiché dans l’outil est celui que vous payez.
Aucun exemple publié pour l’instant.
Idéal pour
- Private reusable voices for authorized speakers
- Multilingual narration that should match a saved reference
Limites connues
- Only clone voices you own or have explicit permission to use.
- Similarity depends on reference quality, transcript accuracy, and language match.
Capacités
- Multilingual speech from a reference voice
- Voice cloning from a short consented sample
- Speed and similarity-mode controls
Entrées
- Consented reference audio
- Exact script and language
- Optional reference transcript and speed
Sorties
- Private generated speech audio
Comparer