VoxCPM

VoxCPM TTS

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

Ku soo biir 5,000 xaraf xaddid

Wrap qoraalka ku SSML tags si loo hubiyo xakamaynta saxda ah:

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

Tags qaabka la doortay fahmo — riix si aad u hoos mid ka mid ah qoraalka aad halkaas oo uu ka dhacaa:

Model this akhriyo qoraalka caadiga ah, sidaas inline tags waa la iska indho tiri. For tag-ku salaysan dareenka, u dhaqaaqo si ay u muujiyaan qaabka sida Orpheus ama Bark.

Define custom pronunciations (word = dhawaaqa):

-12 +12
0.5x 2.0x
Bilaash ah oo leh Piper, VITS, MeloTTS
Your audio soo saaro halkan ka muuqan doonaa. Dooro qaab, ku qor qoraalka, oo guji soo saaro.
Dhaqdhaqaaqa ayaa la soo saaray
0:00
Soo dejisa Soo dejisan.srt Xidhiidhku wuxuu dhamaaday 24h
Free tier: isticmaalka shakhsiga ah. Liisan ganacsi laga bilaabo $ 5 / mo
Jecel TTS.ai? Ka warran saaxiibadaa!

About 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.

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

Taabo oo kala soo bax VoxCPM cod

Eeg

Soo-saarayaasha
OpenBMB
Liisan
Apache 2.0
Qiyaamaha
standard
Xawaaraha
fast
Duubista Codka
Haa
Afaf
English, Chinese
Noocyada ugu badan
2000

VoxCPM cod

Default

English
Caadi Neutral

Default Chinese

Chinese
Caadi Neutral

VoxCPM Su'aalaha La Weydiiyo

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.
← Codadka oo dhan