Real-time AI (audio/video in, voice out) on an M3 Pro with Gemma E2B

In plain words

This project demonstrates real-time AI processing that takes audio and video input and outputs voice responses, running on an M3 Pro Mac using the Gemma E2B model. It is designed for developers interested in on-device AI inference with multi-modal capabilities. The implementation shows how to perform live audio and video processing with voice generation without relying on cloud services, leveraging the M3 Pro's computational power for real-time performance.

written from the facts on this page · September 2026

From the sources

On-device, real-time multimodal AI with features similar to GPT-Live - fikrikarim/parlor

Fully on-device, real-time multimodal AI, with features similar to GPT-Live . Research preview. This is an early experiment. Expect rough edges and bugs. I'm self-hosting a totally free voice AI on my home server to help people learn speaking English. It has hundreds of monthly active users, and I spent weeks improving it until it's almost on par with ChatGPT Advanced Voice. Then, my heart broke when OpenAI released GPT-Live , which is miles ahead of ChatGPT Advanced Voice. GPT-Live is so good that I use it almost every day. It made my app feel obsolete. I either need to redirect my users to GPT-Live, or update the app to match it. I chose to try, with the additional constraint that it had…from github.com

• 
  Conversational AI 2.0 From ElevenLabs2025 · elevenlabs.io · ▲652

  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…

• 
  Play AI2024 · ▲447

  The voice interface of AI

• 
  AI Voices by Asyncflow v1.02025 · async.com · ▲401

  Premium AI voice quality without the premium price tag.

• 
  I open-sourced my AI toy company that runs on ESP32 and OpenAI realtime2025 · github.com · ▲177

  Hi HN! Last year the project I launched here got a lot of good feedback on creating speech to speech AI on the ESP32. Recently I revamped the whole stack, iterated on that feedback and made our project fully open-source—all of the client, hardware, firmware code. This Github repo turns an ESP32-S3 into a realtime AI speech companion using the OpenAI Realtime API, Arduino WebSockets, Deno Edge Functions, and a full-stack web interface. You can talk to your own custom AI character, and it responds instantly. I couldn't find a resource that helped set up a reliable, secure websocket (WSS) AI…

• 
  Listnr 2.02022 · listnr.ai · ▲248

  Create realistic AI Voiceovers within seconds

• 
  Text Reader AI2024 · textreader.ai · ▲158

  Free text-to-speech generator with realistic AI voices

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 19d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 21d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 22d ago · stillwet.art

• 
  Beam.win▲379

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Brila▲1,364

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• 
  I built a tiny LLM to demystify how language models work▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲800

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• 
  Brutalist Concrete Laptop Stand (2024)▲786

  I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

  Life & fun · Apr 2026 · sam-burns.com

• 
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app