VoxCPM

VoxCPM TTS

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

Pierakstīties 5000 rakstzīmju limitam

Aplauzt savu tekstu SSML tagus precīzai kontrolei:

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

Tags izvēlētais modelis saprot — noklikšķiniet, lai iemestu vienu jūsu tekstā, kur tas notiek:

Šis modelis lasa vienkāršu tekstu, tāpēc tiek ignorēti inline tagi. Uz tag-based emocijas, pāriet uz izteiksmīgu modeli, piemēram, Orpheus vai Bark.

Definēt pielāgotu izrunas (vārds = izruna):

-12 +12
0.5x 2.0x
Bez piper, VITS, MeloTTS
Šeit parādīsies jūsu ģenerētais audio. Izvēlieties modeli, ievadiet tekstu un noklikšķiniet ģenerējiet.
Audio veiksmīgi ģenerēts
0:00
Lejupielādēt audio Lejupielādēt.srt Saite beidzas 24h
Bezmaksas līmenis: personīgai lietošanai. Komerclicenci no $5/mo
Mīlestība TTS.ai? Stāsti saviem draugiem!

Par 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.

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

Pārlūkot visu VoxCPM balsis

Īsumā

Izstrādātājs
OpenBMB
Licence
Apache 2.0
Līmeņrādis
standard
Ātrums
fast
Balss klonēšana
Valodas
English, Chinese
Maks. rakstzīmes
2000

VoxCPM balsis

Default

English
Standarta Neutral

Default Chinese

Chinese
Standarta 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.
← Visas balsis