Hacker news

  • Top
  • New
  • Past
  • Ask
  • Show
  • Jobs

Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost (https://narilabs.com)

90 points by toebee 5 days ago | 31 comments | View on ycombinator

recentlypostedj 4 days ago |

Question: How do you plan to differentiate, because there are so many TTS and its constantly changing every month who would become better

asaiacai 5 days ago |

This is really cool work! I'm curious like what do you see as the biggest lever for speeding up TTS models or from a technical perspective that this was a promising direction in the first place to push on. If I were to guess, some distillation but I'm certain there are probably TTS model aware architectural changes that just make inference wayyyy faster?

apimade 5 days ago |

https://apimade.com/audio-compare.html

Added it to my blind TTS model comparison leaderboard. So far Darwin TTS is the open model leading the pack, ElevenLabs is at the lead.

rahimnathwani 5 days ago |

For some reason it switched voices half way through a 33 second clip.

For OP the clip name is nari-nina-01a0a12f-980a-765e-8029-fa56bd23210d.wav

karimf 5 days ago |

This is awesome. Thanks for pushing the audio pareto frontier forward.

Probably far fetched for now, but I think the next big evolution is building the pareto/much cheaper alternative to GPT-Live-1.

The STT/TTS market is quite saturated, while today, there's almost no cheap/open source alternative to GPT-Live-1.

konart 5 days ago |

All TTS generations are too fast. It's almost I'm listening to a podcast on 1.25-1.5x speed.

meatmanek 5 days ago |

> and Qwen3-ASR

Is the ASR inference engine open source as well?

iharnoor 5 days ago |

By next month the competition for TTS will be even more!

Voice models are not winner take all market unlike LLM APIs

Coming here as Developer Relations at AssemblyAI

yoloakki 5 days ago |

You definitely need independent evals by Datapoint AI or someone who can verify your claims about TTS quality

mowmiatlas 5 days ago |

Cool, I’ve released something to the same beat of the dr this weekend as well

https://github.com/loudreader/loudkit

I think real time natural tts should be possible everywhere soon

DylanMerigaud 5 days ago |

Rooting for you on this one.

undefined 5 days ago |

undefined

bilaly 5 days ago |

[flagged]

artexety 5 days ago |

[dead]

ipsum2 5 days ago |

If you're going to announce a TTS model, service, or whatever, you really need demos.

nthypes 5 days ago |

[dead]

FirstClassTree 5 days ago |

[dead]