Nari Qwen3-TTS and Qwen3-ASR
AI
speech models
SHOW HN2026
How HN took it
5 positive, 4 neutral or asking, 0 mixed, 7 critical, out of 16 comments about the project. Thread score -0.10.
Performance: 2 for, 1 againstExecution: 0 for, 2 againstPricing: 0 for, 2 againstIdea: 1 for, 0 againstDocs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive open-source speech performance and cost
From 2 comments
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…
karimf on HNhttps://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.
apimade on HN
Objections
Voice switches or speed issues in generated audio
From 2 comments
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
rahimnathwani on HNAll TTS generations are too fast. It's almost I'm listening to a podcast on 1.25-1.5x speed.
konart on HN
Claims need independent evaluation
From 1 comment
You definitely need independent evals by Datapoint AI or someone who can verify your claims about TTS quality
yoloakki on HN
Market is crowded and changing fast
From 2 comments
Question: How do you plan to differentiate, because there are so many TTS and its constantly changing every month who would become better
recentlypostedj on HNBy 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
iharnoor on HN
Requests
Demos and independent benchmarks
From 2 comments
If you're going to announce a TTS model, service, or whatever, you really need demos.
ipsum2 on HNYou definitely need independent evals by Datapoint AI or someone who can verify your claims about TTS quality
yoloakki on HN
Open-source Qwen3-ASR inference engine
From 2 comments
> and Qwen3-ASR Is the ASR inference engine open source as well?
meatmanek on HNI meant the Nari inference engine for Qwen3-ASR. I'm aware that Qwen3-ASR is open source, but I don't see a repo under https://github.com/nari-labs for nari-qwen3-asr or similar.…
meatmanek on HN
Questions
How will Nari differentiate in a crowded TTS market
From 1 comment
Question: How do you plan to differentiate, because there are so many TTS and its constantly changing every month who would become better
recentlypostedj on HN
Alternatives named
ElevenLabs
From 1 comment
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.
apimade on HN
Darwin TTS
From 2 comments
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.
apimade on HNDarwin TTS is based on Qwen3-TTS https://huggingface.co/zeropointnine/Darwin-TTS-1.7B-Cross-Qwen3Tokenizer
apimade on HN
NVIDIA PersonaPlex
From 1 comment
agreed. we've been doing some work around NVIDIA personaplex 7b, but its quality is quite far from GPT-Live-1, esp in terms of intelligence. Once a good OSS model is out, we'll…
toebee on HN