Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Moonshine Open-Weights STT models

higher accuracy than WhisperLargev3

Details

External ID
47143755
Source
HN
Company
—
Product
Moonshine Open-Weights STT models
Website domain
github.com
Launched
Feb. 24, 2026
Cohort
—
Upvotes
316
Upvotes percentile
0.977088948787062
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

I wanted to share our new speech to text model, and the library to use them effectively. We're a small startup (six people, sub-$100k monthly GPU budget) so I'm proud of the work the team has done to create streaming STT models with lower word-error rates than OpenAI's largest Whisper model. Admittedly Large v3 is a couple of years old, but we're near the top the HF OpenASR leaderboard, even up against Nvidia's Parakeet family. Anyway, I'd love to get feedback on the models and software, and hear about what people might build with it.

Enrichment

Theme
lightweight and on-device AI runtimes
Vertical
Horizontal
Function
Model & infra
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
open-weight speech-to-text models
Manually corrected
False

Could you build this?

No Training frontier-grade speech-to-text models that outperform Whisper Large v3 requires tens of thousands of hours of curated audio datasets, extensive GPU cluster compute, and deep ML research expertise.

What it would actually take: Requires an end-to-end ASR deep learning pipeline implemented in PyTorch/JAX, using conformer or transformer architectures trained on tens of thousands of hours of diverse, multi-speaker audio data across hundreds of GPUs. The difficult challenges are custom acoustic modeling, latency-optimized streaming attention mechanisms, and dataset curation/alignment, requiring dedicated speech research scientists and significant capital for compute.

Discussion

20 comments analyzed.

Competitors mentioned: Whisper, Moonshine, Web Speech API, MacWhisper, VoiceInk

Concerns raised: Lacks streaming support (unlike Moonshine), Slower and less accurate than Parakeet v3 on older Intel CPUs, Model size/memory constraints for edge devices, Battery drain and heat on mobile devices

Feature requests: Add streaming transcription capability, Multilingual performance improvements, M-series and Jetson device optimization, Transformers.js / WebGPU port compatibility

Competitors

Other products that read as similar to this one — 144 launches clear the similarity bar, closest 8 shown.

Attention rank: #15 of 145 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 112 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a model & infra tool for Fintech yet.