TranscriptAI
Meeting AI that understands Japanese soft rejections
What it does
Most meeting AIs miss when someone says no indirectly. TranscriptAI detects nemawashi — Japanese soft rejections like 「検討させてください」(sounds like "I'll consider it", means no). 16 patterns, confidence scored. Keigo formality register via MeCab. Hindi indirect speech. APPI-compliant PII masking. 22% → 94% accuracy across 5 iterations. English · Hindi · Japanese. Live on HuggingFace.
Does a similar job
all alternatives →
- RTReal-time voice chat with AI, no transcription2024 · demo.tincans.ai · ▲33
Hi HN -- voice chat with AI is very popular these days, especially with YC startups (https://twitter.com/k7agar/status/1769078697661804795). The current approaches all do a cascaded approach, with audio -> transcription -> language model -> text synthesis. This approach is easy to get started with, but requires lots of complexity and has a few glaring limitations. Most notably, transcription is slow, is lossy and any error propagates to the rest of the system, cannot capture emotional affect, is often not robust to code-switching/accents, and more. Instead, what…
- IMI made a language tool that forces you to talk2025 · hanasu.ai · ▲5
Hey HN! I created Hanasu.ai after my 9-5 job as a side project. Previously I'd used Duolingo to learn Japanese, but failed spectacularly when I actually spoke with my roommate from Tokyo. Now, after OpenAI improved their Realtime audio model in December and reduced pricing, I spent my entire winter break building. So how does it work? Just choose a daily topic and converse with the AI model: (1) Didn't catch a phrase? Double tap to reveal a transcript. (2) Couldn't understand? Double tap for translations powered by Google. (3) Can't recall that intricate Chinese/Japanese character? Just…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com