🎯
Focusing
bring joy and pursue excellence.
building ultrafast multimodal inference @nari-labs
-
Nari Labs
- nari-labs.com
Pinned Loading
-
nari-labs/dia
nari-labs/dia PublicA TTS model capable of generating ultra-realistic dialogue in one pass.
-
nari-labs/dia2
nari-labs/dia2 PublicTTS model capable of streaming conversational audio in realtime.
-
-
nari-labs/nari-qwen3-tts
nari-labs/nari-qwen3-tts PublicUltrafast Qwen3-TTS: sub-50 ms time-to-first-audio at 10 requests per second.
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




