Callhackernews.com – The missing voice interface for Hacker News

Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription – it anticipates the next likely word before it’s spoken. That makes it both fast (around 150 ms latency) and highly accurate. Scribe v2 Realtime outperforms every low latency transcription model across 30 commonly used EU and Asian languages – 93.5% accuracy, compared to Gemini 2.5 Flash (91.4%), GPT-4o MiniTranscribe (90.7%), and Deepgram Nova 3 (85%). It supports 90+ languages including…

The basics of VUI design

Hi HN, I built Beni (https://thebeni.ai ), a web app for real-time video calls with an AI companion. The idea started as a pretty simple question: text chatbots are everywhere, but they rarely feel present. I wanted something closer to a call, where the character actually reacts in real time (voice, timing, expressions), not just “type, wait, reply”. Beni is basically: A Live2D avatar that animates during the call (expressions + motion driven by the conversation) Real-time voice conversation (streaming response, not “wait 10 seconds then speak”) Long-term memory so the character…

Hello Hacker News, When learning foreign languages, I made the most progress by speaking them throughout the day, every day. So I made a site where you can *speak* to an AI language teacher to practice both listening and speaking. # The product *What I have now:* * Multilingual speech recognition: You can ask a question in English and get an answer in your target language. * Feedback on your grammar. * Suggestions: See examples of what to say next to keep the conversation flowing. * Speed: Choose a lower speed for beginners or a faster one for advanced levels. * Translations: Click to see a…

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…

Greetings HN! I built Voice Isolate to be the simplest way to enhance any speech recording. After hearing so many videos/podcasts with great content but poor audio I realized not everyone can or wants to invest in a pro mic / studio / editing software but figured something simple should be possible now using AI. There are products that do this like Descript or ElevenLabs but I find they’re overcomplicated for many use cases (full blown app designed for professional podcasters, use a convoluted credit system, etc.). As a solo dev I wasn’t sure this was possible to do well but I…