Audio82M official

kokoro

by hexgrad

Kokoro 82M: a tiny, fast TTS model with good preset voices. It runs on any GPU, or on the CPU.

#tts #speech #small #cpu

arcflare gen tts "Hello from ArcFlare" -m kokoro

[ 01 ] // quickstart

┌─ arcflare — zsh // tty1

[ 02 ] // readme

kokoro

Kokoro 82M: a tiny, fast TTS model with good preset voices. It runs on any GPU, or on the CPU.

Get it

arcflare gen setup kokoro --torch cuda

arcflare gen tts "Hello from ArcFlare" -m kokoro

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.

Voices

Pick one with --voice: af_heart (the default), am_michael, bf_emma and more. The first letter is the language: a American English, b British.

arcflare gen tts "Hello there" -m kokoro --voice am_michael

Languages other than English also need espeak-ng installed on the system.

[ 03 ] // relatedmore →

outetts

OuteAI

Audio

OuteTTS 1.0 0.6B: a small TTS model in 14 languages that clones a voice from a clip.

size: 0.6B
vram: ~2 GB
license: Apache-2.0

8% 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

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