Nari Qwen3-TTS and Qwen3-ASR - High-accuracy, low-latency voice AI on the Pareto frontier
Show HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost
Nari Labs' Qwen3-TTS and Qwen3-ASR models lead Coval's voice AI benchmarks, delivering exceptional accuracy and low latency at unbeatable prices. Qwen3-ASR Fast achieves #1 latency (44 ms TTFS) and #2 WER (3.6%), while Qwen3-TTS Fast ranks #2 latency (63 ms TTFA) and #1 WER (3.8%). Both are the cheapest in their categories, making high-performance voice AI accessible for real-time applications like voice agents. Try them free during the public beta and get $20 in credits when you sign up.
Nari Labs leads Coval’s voice AI benchmark by sitting on the quality-latency Pareto Frontier for both Text-to-Speech and Speech-to-Text. We also lead the latency-cost and quality-cost Pareto Frontier out of all publicly available models on the benchmark.
- apimade
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.
- asaiacai
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?
- recentlypostedj
Question: How do you plan to differentiate, because there are so many TTS and its constantly changing every month who would become better
- karimf
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.
- rahimnathwani
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