VoxCPM

VoxCPM TTS

A tokenizer-free TTS model that works in continuous space, outputs 44.1kHz audio, and stays consistent across paragraphs.

दर्ता गर्नुहोस् ५,००० क्यारेक्टर सीमाका लागि

सटीक नियन्त्रणका लागि SSML ट्यागमा तपाईँको पाठ बेर्नुहोस्:

<speak><prosody rate="slow">Slow speech</prosody></speak>

ट्याग चयन गरिएको मोडेल बुझ्छ - यो कहाँ हुन्छ आफ्नो पाठ मा एक गिर गर्न क्लिक:

यो नमूनाले सादा पाठ पढ्दछ, त्यसैले इनलाइन ट्याग उपेक्षा गरिन्छ । ट्याग-आधारित भावनाका लागि, ओर्फिस वा बारक जस्तै अभिव्यक्तिमूलक नमूनामा स्विच गर्नुहोस् ।

अनुकूल उच्चारण परिभाषित गर्नुहोस् (शब्द = उच्चारण):

-12 +12
0.5x 2.0x
पाइपर, VITS, MeloTTS सँग निःशुल्क
तपाईँको सिर्जना गरिएको अडियो यहाँ देखा पर्नेछ । नमूना रोज्नुहोस्, पाठ प्रविष्ट गर्नुहोस्, र सिर्जना गर्नुहोस् क्लिक गर्नुहोस् ।
अडियो सफलतापूर्वक उत्पन्न भयो
0:00
अडियो डाउनलोड गर्नुहोस् डाउनलोड.srt लिङ्क २४ घण्टामा समाप्त हुन्छ
यसको प्रयोग प्राय: व्यक्तिगत रूपमा गरिन्छ। $5/mo बाट व्यावसायिक लाइसेन्स
TTS.ai प्रेम? आफ्नो साथीहरूलाई भन्नुहोस्!

यसका बारेमा 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.

यसका लागि उत्तम: High-fidelity audio, audiobooks, long-form content with voice consistency

सबै ब्राउज गर्नुहोस् VoxCPM आवाज

एक नजरमा

विकासकर्ता
OpenBMB
इजाजतपत्र
Apache 2.0
टर
standard
गति
fast
आवाज क्लोनिङ
हो
भाषा
English, Chinese
अधिकतम क्यारेक्टर
2000

VoxCPM आवाज

Default

English
मानक Neutral

Default Chinese

Chinese
मानक Neutral

VoxCPM TTS - FAQ

Rather than discretizing speech into tokens, VoxCPM models audio in continuous space using flow matching. This helps it retain subtle acoustic detail and produce clean 44.1kHz output.

Yes. It is specifically designed to keep the voice consistent across paragraphs, which makes it well suited to audiobooks and other long passages where other models tend to drift.

Yes. It supports cross-lingual cloning between English and Chinese — for example applying an English reference voice to Chinese speech — from three to ten seconds of audio.
← सबै आवाज