VoxCPM टीटीएस
A tokenizer-free TTS model that works in continuous space, outputs 44.1kHz audio, and stays consistent across paragraphs.
अचूक नियंत्रण करीता SSML टॅग अंतर्गत पाठ्य वेल्ड करा:
<speak><prosody rate="slow">Slow speech</prosody></speak>
निवडलेले नमूना समजून घेणारे टॅग - पाठ्य अंतर्गत एक टाका जेथे ते घडते:
हे मॉडेल सादा पाठ्य वाचते, त्यामुळे इनलाईन टॅग दुर्लक्ष केले जातात. टॅग आधारीत भावना करीता, Orpheus किंवा Bark सारखे अभिव्यक्ती मॉडेल करीता बदलवा.
इच्छिक उच्चारण निश्चित करा (शब्द = उच्चारण):
विषयी VoxCPM
VoxCPM 1.5 by OpenBMB takes an unusual approach: instead of converting speech into discrete tokens, it operates directly in continuous space, which helps it preserve fine acoustic detail. It produces high-fidelity 44.1kHz audio, supports zero-shot voice cloning from three to ten seconds of reference, and maintains a consistent voice across long passages — a common failure point for other models on multi-paragraph text. Its cross-language cloning lets an English reference voice speak Chinese and vice versa. With Apache 2.0 licensing and LoRA fine-tuning support, it is well suited to audiobooks and long-form content where voice consistency over many paragraphs is essential.
सर्वोत्तम: High-fidelity audio, audiobooks, long-form content with voice consistency
सर्व ब्राऊज करा VoxCPM आवाजएक नजर
- डेव्हलपर
- OpenBMB
- परवाना
- Apache 2.0
- टर
- standard
- वेग
- fast
- आवाज क्लोन
- होय
- भाषाName
- English, Chinese
- कमाल अक्षरे
- 2000