VoxCPM

VoxCPM TTS

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

Kulembetsa for 5,000 characters limit

Wrap wanu malemba mu SSML tags kwa kuwongolera moyenera:

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

Tags chosankhidwa chitsanzo amamvetsa - dinani kuti aphe mmodzi m'mawu anu pamene chimachitika:

Izi ndi njira yolemba malemba oyera, kotero ma tag ophatikizidwa amasiya kuganiziridwa. Kuti mupange ma tag ogwirizana ndi maganizo, gwiritsani ntchito njira yolemba malemba monga Orpheus kapena Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free ndi Piper, VITS, MeloTTS
Audio yanu yopangidwa idzawonekera pano. Sankhani mtundu, lemba mawu, ndipo dinani Kupanga.
Audio Yapangidwa Mofulumira
0:00
Pangani Audio Pezani.srt Kugwirizana kumatha mu 24h
Free tier: kugwiritsa ntchito kwa munthu. Lisensi yamalonda kuchokera ku $ 5 / mo
Kukonda TTS.ai? udzauza anzanu!

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

Pezani zonse VoxCPM maganizo

Pa mphindi

Wopanga
OpenBMB
License
Apache 2.0
Mtundu
standard
Kuyenda
fast
Kusintha kwa mawu
Yes
Zilankhulo
English, Chinese
Max characters
2000

VoxCPM maganizo

Default

English
Choyambirira Neutral

Default Chinese

Chinese
Choyambirira Neutral

VoxCPM TTS — Mafunso Ofala

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.
← Mawu onse