Overview
News
Technologies
Salaries
Products
People
Growth
Financials
Overview
Low-latency, realtime multimodal model serving from Nari Labs, starting with speech at 50 ms time to first audio.
News
Pushing the Speed-Cost Frontier for Qwen3-TTS
10 RPS with p95 TTFA under 50 ms on a single H100: how we optimized Qwen3-TTS serving.
Read more
Report
Dia 1.6B - a Hugging Face Space by nari-labs
This app turns any written text into a natural-sounding voice recording. You can also upload a short (10 s) audio clip and its transcription to guide the voice style. After setting a few generatio...
Read more
Report