benchmarks

(★ 9)

Open-source benchmarking tool from Nari Labs

Owner Repos

dia ★ 19,369

A TTS model capable of generating ultra-realistic dialogue in one pass.

Python
dia2 ★ 1,169

TTS model capable of streaming conversational audio in realtime.

Python
nari-qwen3-tts ★ 105

Ultrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second.

Python

File Explorer

ZIP Download
  • .gitignore
  • LICENSE
  • README.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example
// repository documentation