slotvox
End-to-end spoken language understanding toolkit: a small trainable neural audio codec with RVQ, joint intent-and-slot models over speech features, streaming partial intents, a speech-LLM instruction data pipeline, and turn-level evaluation with reproducible reports. NumPy core with a CPU-only torch extra; synthetic data only, fully offline.
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
GITHUB · launched Sep 26, 2026 · 36 upvotes (top 23%) · 0 views
Niche: speech and voice ai models · 143 launches, 7 in the last 7 days ▼ -30% · Explore this niche →
Category and tags
- Horizontal
- Model & infra
- Developer
- AI-native
- Hobby / open-source project
- end-to-end
- instruction-data
- intent-detection
- neural-audio-codec
- numpy
- python
- +5 more
Visit website ↗ Source listing ↗
More like this: all 143 launches in speech and voice ai models →
Could you build this?
No Training custom neural audio codecs with residual vector quantization (RVQ) and joint intent/slot models from scratch requires specialized machine learning and speech processing research expertise.
What it would actually take: Architecture consists of custom PyTorch/NumPy acoustic encoders, vector-quantized latent representations (RVQ), streaming recurrent/transformer SLU heads, and synthetic speech synthesis pipelines. The hardest parts are acoustic codec training stability, low-latency streaming discretization on CPU without quantization noise, and domain-specific audio ML engineering.
Competitors
Other products that read as similar to this one : 1318 launches clear the similarity bar, closest 8 shown.
Attention rank: #336 of 1319 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 331 days after the earliest competitor.
- speechloom · github · 2026-09-09 · 31 upvotes · similarity 0.66
- voxweave · github · 2026-09-09 · 32 upvotes · similarity 0.65
- wavrail · github · 2026-09-26 · 31 upvotes · similarity 0.65
- KugelAudio: A multilingual voice AI model you can run in your own cluster. · yc · 2026-05-27 · 8 upvotes · similarity 0.62
- Speko: OpenRouter for Voice · yc · 2026-07-29 · 14 upvotes · similarity 0.61
- echoparley · github · 2026-10-14 · 22 upvotes · similarity 0.61
- caramel · github · 2026-11-10 · 28 upvotes · similarity 0.60
- maya2-native · github · 2026-10-26 · 19 upvotes · similarity 0.60
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.