Teks ke Tutur Agen AI Muzik Tutur ke Teks Klon Suara Rekabentuk Suara Pasaran Lebih
Lapor Pepijat / Permintaan Ciri
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 Aksara · Daftar untuk 5,000 per generasi →
Daftar masuk had 5,000 aksara

Lilitkan teks anda dalam tag SSML untuk kawalan tepat:

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

Tag model dipilih memahami - klik untuk jatuhkan satu ke dalam teks anda di mana ia berlaku:

Model ini membaca teks biasa, jadi tag dalam baris diabaikan. Untuk emosi berdasar tag, beralih ke model ekspresif seperti Orpheus atau Bark.

Tetapkan sebutan tersendiri (perkataan = sebutan):

-12 +12
0.5x 2.0x
Bebas dengan Piper, VITS, MeloTTS
Audio yang dijana akan muncul di sini. Pilih model, masukkan teks, dan klik Janakan.
Audio Dijana Dengan Berjaya
0:00
Muat turun Audio Muat turun.srt Pautan luput dalam 24 jam
Tahap percuma: penggunaan peribadi. Lesen Komersial dari $5/mo
Cinta TTS.ai? Beritahu kawan-kawan anda!

Tentang 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.

Terbaik untuk: Fast English generation on low-VRAM hardware, quick previews

Layari semua Kani TTS 2 suara

Dengan sekejap mata

Pemaju
NineNineSix
Lesen
Apache 2.0
Tajuk
free
Kelajuan
fast
Klon suara
Tidak
Bahasa
English
Aksara maksimum
1000

Kani TTS 2 suara

Default

English
Piawai Neutral

Kani TTS 2 TTS - FAQ

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.
← Semua suara