Metinden Söze AI Agentler Musiqa Sözden metin Ses Klonlama Ses Dizaýny Bazar _Ýaşa
Hadysa / Fe'l-aşgabat soragyny habar ber
Kani TTS 2

Kani TTS 2 TTS

An ultra-lightweight 400M English model that runs in just 3GB of VRAM at a 0.2 real-time factor.

0/500 karakterler · 5000 per generation üçin ýaz →
_Gün tertibi 5000 karakter çäk

Metini SSML taglarda dolap dogry kontrol üçin:

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

Saýlanan model aňlaýan taglar — birini metinde goýmak üçin basyň:

Bu model ýönekeý metin okaýar, şonuň üçin hatda taglar gözden düşürilýär. Tag-based emotions for, switch to an expression model like Orpheus or Bark.

Öz sözleriň terjimesini belli et (söz = terjime):

-12 +12
0.5x 2.0x
Piper, VITS, MeloTTS bilen azat
Siziň döreden audioňyz şu ýerde görüner. Bir model saýlaň, metin girin we döred
Ses mübärek bejerildi
0:00
Ses ýükle .srt ýükle Baglanyşyk 24 sagadyň içinde gutarýar
Özüni ulan $5/mo-dan söwda lisenziýasy
TTS.ai-ni söýýäňmi? Dostlaryňa aýt!

Habar Kani TTS 2

Kani-TTS-2 by NineNineSix is an ultra-lightweight 400M-parameter text-to-speech model built on a Liquid AI LFM2 backbone with NVIDIA's NanoCodec. It runs in just 3GB of VRAM and generates roughly ten seconds of speech in about two seconds on an A100 — a real-time factor near 0.2. The current public release ships an English-only checkpoint and, unlike its predecessor, does not expose the speaker-embedding hook needed for voice cloning. Its strength is fast, low-cost English generation on modest hardware, which makes it a good fit for quick previews and high-volume English narration. It is released under Apache 2.0 and offered on the free tier.

Muňa iň gowy: Fast English generation on low-VRAM hardware, quick previews

Ehlini _Gözle Kani TTS 2 sesler

Bir seretseň

Developer
NineNineSix
Lisenziýa
Apache 2.0
_Göçür
free
Tizlik
fast
Ses klonlamak
_Ýok
Diller
English
Maks. karakterler
1000

Kani TTS 2 sesler

Default

English
_Öň bellenen Neutral

Kani TTS 2 TTS - Gynançly Soraglar

It runs in just 3GB of VRAM and produces about ten seconds of speech in roughly two seconds on an A100 — a real-time factor near 0.2 — thanks to its 400M-parameter LFM2 backbone and NanoCodec.

No. The current v2 release removed the public speaker-embedding hook, so cloning is not available. For cloning, use Chatterbox, IndexTTS-2, or GPT-SoVITS.

English only. The public release ships a single English checkpoint; for non-English speech, use a model like Kokoro or MeloTTS.
← Ehli Sesler