Fish Audio Launches S2.1 Pro: 90ms Latency TTS Across 83 Languages
testingcatalog · x · 2026-07-29
Fish Audio has launched S2.1 Pro, a production-ready text-to-speech model optimized for real-time conversational voice.
Key features:
- Ultra-low latency: 90ms time-to-first-audio, enabling natural turn-taking in live dialogue.
- Multilingual: A single voice identity covers 83 languages.
- Inline emotion control: Supports free-form bracket tags (e.g., [whispers sweetly]) for dynamic emotion steering.
- Voice cloning: Captures tone and style from just 10-30 seconds of reference audio.
- Developer-friendly: Offers a free tier and integrates into agent workflows via MCP and agent-skill support.
Related event: Fish Audio Launches S2.1 Pro Voice Model with $52M Seed Funding(11 posts)→
More from Models
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Thrive Holdings launches real-work AI evals from 75+ businesses, benchmarking 13 models — samaysham · 2026-10-16
- Microsoft's MAI-Transcribe now handles 61% of all transcription on OpenRouter — mustafasuleyman · 2026-10-16
- Reflection AI Releases Open-Weight 501B MoE Beam for Agentic Coding on AWS — AWS ML Blog · 2026-10-16
- Dev RL-tunes Qwen 27B against slop with Meta's XAR method, lands top-4 on EQbench — Mysterious_Hearing14 · 2026-10-16
- HotDogBench tests 10 LLMs on 1,000 hot dog photos — all within each other's error bars — josh_wills · 2026-10-16