VoxCPM

VoxCPM TTS

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

Prihlásiť sa na odber Limit 5 000 znakov

Zabaliť text do SSML značiek pre presnú kontrolu:

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

Značky, ktorým vybraný model rozumie — kliknutím ich umiestnite do textu tam, kde sa vyskytujú:

Tento model číta obyčajný text, takže vnorené značky sa ignorujú.Pre emócie založené na značkách prejdite na expresívny model ako Orpheus alebo Bark.

Definovať vlastné výslovnosti (slovo = výslovnosť):

-12 +12
0.5x 2.0x
Zadarmo s Piper, VITS, MeloTTS
Vyberte si model, zadajte text a kliknite na tlačidlo Generovať.Generate.
Audio generované úspešne
0:00
Stiahnuť audio na stiahnutie Stiahnuť.srt súbor Platnosť odkazu vyprší za 24h
Bezplatná úroveň: osobné použitie. Komerčná licencia od 5 USD/mesiac
Láska TTS.ai? Povedzte svojim priateľom!

O nás 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.

Najlepšie pre: High-fidelity audio, audiobooks, long-form content with voice consistency

Prehľadávať všetky VoxCPM hlasy

Na prvý pohľad

Vývojár
OpenBMB
Licencia
Apache 2.0
Zvieratá
standard
Rýchlosť
fast
Klonovanie hlasu
Áno
Jazyky
English, Chinese
Max. počet znakov
2000

VoxCPM hlasy

Default

English
Štandardné Neutral

Default Chinese

Chinese
Štandardné Neutral

VoxCPM TTS — Často kladené otázky

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.
← Všetky hlasy