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.

Cofrestru am gyfyngiad 5,000 nod

Amlapio' ch testun mewn tagiau SSML er mwyn cael rheoli cywir:

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

Tags y deall y model dewisiedig - cliciwch i daflu un i' ch testun lle mae' n digwydd:

Mae'r model yma yn darllen testun plaen, felly anwybyddir tagiau mewnlin. I ddelweddu teimlad yn seiliedig ar dagiau, newidiwch i ddelweddu mynegiant fel Orpheus neu Bark.

Diffinio ynganiad addasiedig (gair = ynganiad):

-12 +12
0.5x 2.0x
Am ddim gyda Piper, VITS, MeloTTS
Bydd eich sain a gynhyrchwyd yn ymddangos yma. Dewiswch ddull, rhowch destun, a chliciwch Creu.
Creuwyd Sain yn Llwyddiannus
0:00
Lawrlwytho Sain Lawrlwytho.srt Mae'r cyswllt yn darfod mewn 24 awr
Haen rhad: defnydd personol. Trwydded fasnachol o $5/mis
Gwneud hwn yn eich llais eich hun Clonio llais mewn 30 eiliad
Hoffwch TTS.ai? Meddwl am eich ffrindiau!

Am 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.

Gorau ar gyfer: Fast English generation on low-VRAM hardware, quick previews

Pori Popeth Kani TTS 2 Saesneg

Yn syth

Datblygwr
NineNineSix
Trwydded
Apache 2.0
o Fawrth
free
Cyflymder
fast
Clonio llais
Na
Iaith:
English
Uchafswm nodau
1000

Kani TTS 2 Saesneg

Default

English
Arferol Neutral

Kani TTS 2 TTS - Cwestiynau Cyffredin

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.
← Pob llais