# Here's a peek inside our vault of resources

News, guides, resources from Smallest

- \
\
Why Streaming Architecture is Non-Negotiable for Real-Time Voice Agents\
\
Wasim Madha\
\
Dec 18, 2025](/content/blog/why-streaming-architecture-is-non-negotiable-for-real-time-voice-agents/index.html)

- \
\
Why Nvidia GPUs Struggle with Real-Time Speech Inference\
\
Prithvi Bharadwaj\
\
Dec 18, 2025](/content/blog/why-nvidia-gpus-struggle-with-real-time-speech-inference/index.html)

- \
\
Voice Cloning AI in Production: Architecture, Latency, and Ethical Safeguards\
\
Sumit Mor\
\
May 5, 2026](/content/blog/voice-cloning-ai-in-production-architecture-latency-and-ethical-safeguards/index.html)

- \
\
The Limits of Large Fused Kernels on Nvidia GPUs: Why Real-Time AI Inference Needs More\
\
Prithvi Bharadwaj\
\
Dec 18, 2025](/content/blog/the-limits-of-large-fused-kernels-on-nvidia-gpus-why-real-time-ai-inference-needs-more/index.html)

- \
\
The Latency Problem: The One Thing Killing Your Voice AI Experience (And How to Fix It)\
\
Akshat Mandloi\
\
Dec 18, 2025](/content/blog/the-latency-problem-the-one-thing-killing-your-voice-ai-experience-and-how-to-fix-it/index.html)

- \
\
Integrating Smallest AI Voice Models with TrueFoundry AI Gateway\
\
May 14, 2026](/content/blog/integrating-smallest-ai-voice-models-with-truefoundry-ai-gateway/index.html)

- \
\
Smallest AI Joins LiveKit's Plugin Ecosystem- Real-Time Voice AI with Pulse STT and Lightning TTS\
\
May 7, 2026](/content/blog/smallest-ai-joins-livekit-s-plugin-ecosystem--real-time-voice-ai-with-pulse-stt-and-lightning-tts/index.html)

- \
\
Rewriting TTS Inference Economics: Lightning V2 on Tenstorrent Achieves 4× Lower Cost Than NVIDIA L40S\
\
April 17, 2026](/content/blog/rewriting-tts-inference-economics-lightning-v2-on-tenstorrent-achieves-4%C3%97-lower-cost-than-nvidia-l40s/index.html)

- \
\
Introducing Lightning V3: A Text-to-Speech Model Designed for Conversational Voice Agents\
\
March 24, 2026](/content/blog/introducing-lightning-v3/index.html)

- \
\
The generalization issues of phoneme based text to speech models\
\
February 19, 2026](/content/blog/the-generalization-issues-of-phoneme-based-text-to-speech-models/index.html)

- \
\
Inference Optimization - How to Optimize a Model for Latency?\
\
December 18, 2025](/content/blog/inference-optimization-how-to-optimize-a-model-for-latency/index.html)

- \
\
Evaluating the Lightning-v2 Multilingual TTS Model\
\
December 18, 2025](/content/blog/evaluating-the-lightning-v2-multilingual-tts-model/index.html)