AmphiVox
Just answer. We'll handle the form.
What it does
AmphiVox enables any form to have a voice concierge embedded into it. Have a coversation with the agent and fill the fields; several at once, in your own language. We currently support over 45 languages. Import a form you already have from a PDF or photo, or drop the same voice agent onto a form already live on your site. Built for teams collecting information from people who'd rather talk than type. Working beta — try it on a real form today.
Build AI voice forms that turn natural speech into structured responses. Support 45+ languages and route submissions to AmphiVox, Google Sheets, or Excel.
An AI voice assistant asks the questions, understands natural answers, and fills every field as the conversation happens. 45+ supported languages, including 10+ Indian languages. Across them the assistant follows a mix of English and the local language instead of forcing one; elsewhere, answering in your own language works even when English slips in. The creator's output stays structured English. AmphiVox does more than transcribe. It resolves natural speech into the form's real field structure, then keeps validation and review visible. One turn, four fields. No prompt-per-input exchange, no rephrasing to match the form's wording. The assistant asks related questions together, and extra…from amphivox.com
Does the same job
all alternatives →
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 · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d 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 · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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 · 16d ago · simedw.com