Tagged: latency

7 articles

Latest

Gradium's new TTS beats ElevenLabs by 15 points on the calls that actually lose money

Why Your Voice AI Feels Slow Even When Your LLM's TTFT Looks Fast

OpenAI's Ultrafast tier hits 750 tokens/second with GPT-5.6 Sol on Cerebras

NVIDIA drops open TTS model hitting 32ms first audio, covering 12 languages

Why GPT-4.1 Costs Double Claude Sonnet Despite Cheaper Tokens

vLLM's long prompts silently choke fast token generation for everyone

TNG runs 5,000+ LLM inferences per hour on 24 H100s—here's the prefill/decode trade-off