Text-to-Speech by fishaudio — Detected via huggingface trending
We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions.
When s2-pro becomes available, it will appear on our LLM Leaderboard with full scoring, benchmarks, and pricing. Check our New AI Models page for the latest releases.
s2-pro was first detected on March 15, 2026 via huggingface trending. We are tracking it for general availability. Check back for updates.
Once s2-pro becomes available, we will provide full benchmark comparisons, pricing analysis, and capability breakdowns on our LLM Leaderboard.
Pricing details have not been confirmed yet. Based on fishaudio's pricing history, we will update this page as soon as official pricing is announced.