VoxCPM

VoxCPM TTS

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

Langganan for 5,000 characters limit

Ngresiki teks ing tag SSML kanggo kontrol presisi:

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

Tag kang dipahami model kang dipilih - klik kanggo ngethok siji ing teks sampeyan ing ngendi iku kedadeyan:

Model iki maca teks biasa, mula tag ing baris diabaikan. Kanggo emosi berbasis tag, ganti menyang model ekspresif kaya Orpheus utawa Bark.

Nyathet tembung-tembung standar (kata = tembung):

-12 +12
0.5x 2.0x
Bebas karo Piper, VITS, MeloTTS
Audio sing digawé bakal katon ing kene. Pilih modél, ketik teks, lan pencet Ngembangaké.
Audio Digawé kanthi Sukses
0:00
Unduh Audio Download.srt Link expires in 24h
Ing basa Indonésia, iku tegesé: pribadi. Lisénsi komersial saka $5/mo
TTS.ai? Nyathet kanca-kancamu!

Ngendi 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.

Paling apik kanggo: High-fidelity audio, audiobooks, long-form content with voice consistency

Jajal kabeh VoxCPM swara

Ing cetha

Pangembang
OpenBMB
Lisénsi
Apache 2.0
Tanggal
standard
Kecepatan
fast
Kloning swara
Ya
Basa
English, Chinese
Aksara paling akèh
2000

VoxCPM swara

Default

English
Standar Neutral

Default Chinese

Chinese
Standar Neutral

VoxCPM 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.
← Sekabehing swara