edgedecision
Local voice control for Home Assistant on a Raspberry Pi 5: streaming speech-to-text (EdgeSTT) and a small non-generative decision engine (EdgeDecision). 9 languages, no cloud, no LLM.
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 84 launches in voice productivity assistants — see how it stacks up on momentum and crowding →
397 other launches read as similar to this one →
Details
- External ID
- 1406366206
- Source
- GITHUB
- Company
- —
- Product
- edgedecision
- Website domain
- github.com
- Launched
- Oct. 5, 2026
- Cohort
- —
- Upvotes
- 11
- Upvotes percentile
- 0.14
- Tags
- hacs, home-assistant, home-assistant-addon, local-first, onnx, raspberry-pi, speech-to-text, voice-assistant, wyoming
Enrichment
- Niche
- voice productivity assistants
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Prosumer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- local voice control for home assistant
- Manually corrected
- False
Could you build this?
Partial While Home Assistant integrations are common, running real-time streaming speech-to-text across 9 languages alongside a deterministic intent parser on an edge device (Raspberry Pi 5) requires strict optimization and embedded ML tuning.
What it would actually take: The system utilizes embedded streaming STT engines (like sherpa-onnx, whisper.tflite, or Vosk) optimized for ARM NEON instructions and CPU memory bounds on the Pi 5. The intent parser uses grammar-based or lightweight deterministic finite-state automata (FSTs) integrated via Home Assistant's WebSocket/REST APIs. Building it requires expertise in embedded systems, on-device audio streaming buffers, and localized multilingual acoustic model compression.
Competitors
Other products that read as similar to this one — 397 launches clear the similarity bar, closest 8 shown.
Attention rank: #336 of 398 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 335 days after the earliest competitor.
- EdgeSpeech, on-device speech-to-speech for React Native · hn · 2026-07-09 · 5 upvotes · similarity 0.55
- speakrail · github · 2026-10-04 · 93 upvotes · similarity 0.52
- RayCodes_sanoTTS · github · 2026-09-10 · 7 upvotes · similarity 0.52
- VoxAster · github · 2026-10-04 · 12 upvotes · similarity 0.51
- Speko: OpenRouter for Voice · yc · 2026-07-29 · 14 upvotes · similarity 0.51
- Speko · ph · 2026-08-27 · 266 upvotes · similarity 0.50
- doubao-say · github · 2026-09-14 · 64 upvotes · similarity 0.50
- saystack · github · 2026-10-01 · 11 upvotes · similarity 0.49
Other launches for this product
- No other launches for this product.