Audio2B official

voxcpm2

by OpenBMB

VoxCPM2: the highest-quality model here, with 48 kHz output in 30 languages. It wants a CUDA GPU.

#tts #speech #high-quality #multilingual

arcflare gen tts "Hello from ArcFlare" -m voxcpm2

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

voxcpm2

VoxCPM2: the highest-quality model here, with 48 kHz output in 30 languages. It wants a CUDA GPU.

Get it

arcflare gen setup voxcpm2 --torch cuda

arcflare gen tts "Hello from ArcFlare" -m voxcpm2

It writes a .wav to the current folder (-o to choose). The model gets its own Python environment, so it can't break another one. The first run downloads the weights. On an AMD GPU under Windows, use --torch-from <python> instead of --torch cuda. See Speech.

arcflare gen tts "Hello there" -m voxcpm2

Its model card asks for CUDA 12+ and PyTorch 2.5+, so this is an NVIDIA model in practice.

[ 03 ] // relatedmore →

qwen3-tts

Alibaba Qwen

Audio

Qwen3-TTS: Qwen's open speech model. Preset voices, 10 languages, tone control from a text instruction, and a variant that clones a voice from 3 seconds of audio.

size: 1.7B
vram: ~6 GB
license: Apache-2.0

25% of a 24 GB card

#tts #speech #multilingual

chatterbox

Resemble AI

Audio

Chatterbox: clones a voice from a few seconds of audio, with 23 languages in its multilingual model. MIT.

size: 0.5B
vram: ~4 GB
license: MIT

17% of a 24 GB card

#tts #speech #voice-cloning

kitten-tts-2

KittenML

Audio

Kitten TTS 2: a 1.7B speech model that clones a voice from 5-30 seconds of audio, with 47 built-in voices, emotion tags and a 0.95 GB ternary download that runs on the CPU too.

size: 1.7B
vram: ~4 GB
license: Stellon Labs Community

17% of a 24 GB card

#tts #speech #voice-cloning