Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

vocence-tts-fish-s2 – AI Model by bignova19790117 | AlphaNeural AI

You can deploy this model and start earning money today!

bignova19790117/
vocence-tts-fish-s2

like

0

Views

No views yet

Vocence TTS — Fish Audio S2 Pro (5B)

Voice-cloning TTS miner using Fish Audio S2 Pro.

Model: fishaudio/s2-pro (5B params: 4B slow-AR + 400M fast-AR)
Architecture: Dual-AR with RVQ codec (10 codebooks, ~21Hz)
Voice cloning: LibriVox narrator reference clips (3 female, 3 male)
Features: Inline emotion control via [tag] syntax, RL-aligned (GRPO)
Ranking: #1 on TTS-Arena2, WER 0.99%, ATT 0.515