Real-time voice chat with AI, no transcription
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…
In plain words
This product enables direct voice conversations with AI by feeding audio directly to a language model, bypassing traditional transcription steps. It's designed for users who want faster, more natural voice interactions without the delays and errors that come from converting speech to text first. The approach captures emotional nuance and handles accents and code-switching better than conventional cascaded systems, since the AI processes raw audio directly rather than relying on potentially lossy transcription intermediaries.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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 if we fed audio directly to the LLM - LLM's are really smart, can they figure it out? This approach is faster (we skip transcription decoding) and less lossy/more robust because the big language model should be smarter than a smaller transcription decoder. I've trained a model in just that fashion. For more architectural information and some training details, see this first post: https://tincans.ai/slm . For details about this model and some ideas for how to prompt it, see this post: https://tincans.ai/slm3 . We trained this on a very limited budget but the model is able to do some things that even GPT-4, Gemini, and Claude cannot, eg reasoning about long-context audio directly, without transcription. We also believe that this is the first model in the world to conduct adversarial attacks and apply preference modeling in the speech domain. The demo is unoptimized (unquantized bf16 weights, default Huggingface inference, serverless speed bumps) but achieves 120ms time to first token with audio. You can basically think of it as Mistral 7B, so it'll be very fast and can also run basically anywhere. I am especially optimistic about embedded usage -- not needing the transcription step means that the resulting model is smaller and cheaper to use on the edge. Would love to hear your thoughts and how you would use it! Weights are Apache-2 and on Hugging Face: https://huggingface.co/collections/tincans-ai/gazelle-v02-65...
Does the same job
all alternatives →- RTReal-time AI Voice Chat at ~500ms Latency2025 · github.com · ▲524
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 · 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 · 27d ago · cactuscompute.com
Launched alongside, March 2024
the whole month →
- 3Y
Life & fun · 2024 · github.com
Microlaunch▲1,116Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
