VoxCPM

VoxCPM TTS

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

Aliĝi for 5, 000 character limit

Envolvu vian tekston en SSML- etikedojn por preciza kontrolo:

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

Etikedoj kiujn la elektita modelo komprenas - klaku por meti unu en vian tekston kie ĝi okazas:

This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.

Difini proprajn elparolojn (vorto = elparolo):

-12 +12
0.5x 2.0x
Libera kun Piper, VITS, MeloTTS
Via generita sono aperos tie ĉi. Elektu modelon, entajpu tekston, kaj alklaku Generi.
Sondosiero sukcese generita
0:00
Elŝuti sonon Elŝuti.srt Ligo eksvalidiĝas post 24 horoj
Libera programaro: persona uzo. Komerca licenco ekde $5/mo
Ĉu vi ŝatas TTS.ai? Diru al viaj amikoj!

Pri 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.

Plej bona por: High-fidelity audio, audiobooks, long-form content with voice consistency

Foliumi ĉiujn VoxCPM voĉoj

Unu rigardo

Programisto
OpenBMB
Licenco
Apache 2.0
Tamuz
standard
Rapideco
fast
Voĉo- klonado
Jes
Lingvoj
English, Chinese
Maksimuma nombro da signoj
2000

VoxCPM voĉoj

Default

English
Defaŭlta Neutral

Default Chinese

Chinese
Defaŭlta 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.
← Ĉiuj voĉoj