Hitoku Draft
Context aware local assistant
Details
- External ID
- 48402082
- Source
- HN
- Company
- —
- Product
- Hitoku Draft
- Website domain
- hitoku.me
- Launched
- June 4, 2026
- Cohort
- —
- Upvotes
- 21
- Upvotes percentile
- 0.755464480874317
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
Hi guys.I have been working on Hitoku Draft, an open-source, voice-first AI assistant that runs entirely locally. I posted about it already, and now it has also transcription with voice editing. Looking for feedback, as I found that outside tech circles other people still do not use this tech much.It's context-aware, in the sense that it reads your screen, documents, and active app to understand what you're working on. You can ask about PDFs, reply to emails, create calendar events, use web search, editing text, all by voice.You can download a compiled version for free with the code HITOKUHN2026 https://hitoku.me/draft/ (base price is 5 dollars)It supports Gemma 4 and Qwen 3.5 for text generation, plus multiple STT backends (Parakeet, Qwen3-ASR).Examples: - Gemma4 in action, https://www.youtube.com/watch?v=OgfI-3YjEVU - query a pdf document, https://www.youtube.com/watch?v=ggaDhut7FnU - reply to email, https://www.youtube.com/watch?v=QFnHXMBp1gA - and the usual voice dictation (with optional polishing)I currently use it a lot with Claude Code and Logseq. Now with some friends we are also building a new cross-platform version. The goal is on the long run to have AI interactive local models serving people and professionals.
Enrichment
- Theme
- voice dictation and control tools
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- context aware local ai assistant
- Manually corrected
- False
Could you build this?
Yes A macOS desktop utility wrapping whisper.cpp or Apple Speech frameworks with a local LLM via MLX or llama.cpp for voice-to-text and editing.
Discussion
8 comments analyzed.
Competitors mentioned: Gemma 4, Other multimodal LLMs
Concerns raised: Abandonware risk on Gumroad - developers stop supporting products within months, App Store requires feature stripping, complicates distribution, Multiple rough edges and bugs in current version, STT/dictation functionality unreliable and inconsistent, Unclear value proposition - marketing doesn't clearly explain what it does
Feature requests: Option to dismiss text preview popup before auto-vanish, TTS voice preview/demo without triggering full speech, Fix Ctrl+S dictation to work reliably with Gemma 4, Clearer documentation of multimodal LLM requirements
Competitors
Other products that read as similar to this one — 103 launches clear the similarity bar, closest 8 shown.
Attention rank: #26 of 104 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 210 days after the earliest competitor.
- Ito AI, open source smart dictation · hn · 2025-11-06 · 16 upvotes · similarity 0.41
- Voice-first todo list that updates live as you talk · hn · 2025-12-27 · 5 upvotes · similarity 0.41
- VoiceCap · ph · 2026-09-19 · 100 upvotes · similarity 0.40
- Local-AI-Voice-Studio · github · 2026-09-13 · 13 upvotes · similarity 0.39
- TTSLab · hn · 2026-02-23 · 5 upvotes · similarity 0.39
- Clippy · hn · 2026-03-18 · 5 upvotes · similarity 0.39
- FaceTime-style calls with an AI Companion (Live2D and long-term memory) · hn · 2026-01-25 · 34 upvotes · similarity 0.38
- I built a voice AI that responds like a real woman · hn · 2026-03-25 · 6 upvotes · similarity 0.38
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.