VoxCPM

VoxCPM TTS

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

Skráðu þig inn fyrir 5.000 stafa takmörk

Wrap texta í SSML tags fyrir nákvæma stjórn:

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

Merki sem valið líkan skilur — smelltu til að sleppa einu í textann þinn þar sem það gerist:

Þetta líkan les venjulegan texta, þannig að innlínumerki eru hunsuð. Fyrir merki sem byggja á tilfinningum, skiptu yfir í tjáningarlíkan eins og Orpheus eða Bark.

Skilgreindu sérsniðna framburð (orð = framburð):

-12 +12
0.5x 2.0x
Frjáls með Piper, VITS, MeloTTS
Hljóðskráin þín birtist hér. Veldu líkan, sláðu inn texta og smelltu á Búa til.
Hljóð búið til
0:00
Sækja hljóð Sækja.srt Tengill rennur út eftir 24 klst
Frjáls tier: persónuleg notkun. Viðskiptaleyfi frá $ 5 / mánuði
Elska TTS.ai? Segðu vinum þínum!

Um 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.

Best fyrir: High-fidelity audio, audiobooks, long-form content with voice consistency

Skoða allt VoxCPM raddir

Í hnotskurn

Forritari
OpenBMB
Leyfi
Apache 2.0
Tími
standard
Hraði
fast
Raddklóðun
Tungumál
English, Chinese
Hámarksstafir
2000

VoxCPM raddir

Default

English
Sjálfgefið Neutral

Default Chinese

Chinese
Sjálfgefið Neutral

VoxCPM TTS — Algengar spurningar

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.
← Allar raddir