Fish Audio Launches Free TTS API: Squeezing 125 Audio Tokens/sec on a Single H200
rohanpaul_ai · x · 2026-07-30
Fish Audio announced that its most advanced voice model, S2.1 Pro, is now available to developers as a free Text-to-Speech (TTS) API, supporting 83 languages with unlimited usage under a Fair Use policy.
To break the industry norm that high-quality voice models must be paid, Fish Audio detailed its underlying compute optimization: every request runs on a single NVIDIA H200 GPU. By using a custom FP8 software stack and a "pingpong" scheduler to eliminate idle time, they achieve an RTF of 0.17 and a throughput of 125 audio tokens per second.
Related event: Fish Audio Launches Free TTS API Optimized for Single H200 GPU(2 posts)→
More from Infra
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16
- SkyRL ships Day-0 RL support for Beam with +62% LoRA decode throughput in vLLM — vllm_project · 2026-10-16
- DFlash2 delivers up to 3.03x decode-only speedup for Beam across five benchmarks — vllm_project · 2026-10-16
- vLLM's Beam serving kernels cut GB200 forward time from 8.15 to 6.47 ms at TP8 batch 128 — vllm_project · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- Nemotron 3.5 Bolt runs 16 concurrent streams on a single DGX Spark — NVIDIAAI · 2026-10-16