Gabber

What it does

Gabber.dev is the infra powering real-time, emotionally expressive AI voice apps—now with ultra-low-latency, hyper-expressive and realistic Orpheus Voice TTS at 90% less cost than ElevenLabs or Play.ht.

Realtime VLM, TTS, and STT orchestration for making realtime AI apps that can do anything. Cross-device, multi-participant, multi-input realtime AI apps. Use Gabber's graph-based orchestration system to build apps powered by the best VLMs and LLMs. Your AI personal trainer watches your form, counts your reps, and pushes you to your limits. Your AI personal trainer watches your form, counts your reps, and pushes you to your limits. Build complex real-time apps fast with a drag-and-drop visual builder. Connect inference with logic and state to prototype and production in minutes. Create apps that see, hear, and act, powered by Gabber’s sub-second orchestration engine. Use Gabber to design,…from gabber.dev

• 
  I built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570

  I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural…

• 
  Kitten TTS – 25MB CPU-Only, Open-Source TTS Model2025 · github.com · ▲1,003

  Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…

• 
  gpt-realtime-1.5 by OpenAIFeb 2026 · developers.openai.com · ▲300

  Tighter instruction adherence in speech agents

• 
  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…

• 
  Outspeed2024 · ▲462

  Platform for realtime voice and video AI

• 
  Gan.AI TTS Model & API Playground2024 · ▲333

  First TTS model to support all 22 Indic languages + English

• 
  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

• 
  I built a hardware processor that runs Python▲983

  Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…

  Dev tools · 2025 · runpyxl.com

• 
  Unsure Calculator – back-of-a-napkin probabilistic calculator▲930

  The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.

  Life & fun · 2025 · filiph.github.io

• 
  I built an AI that turns GitHub codebases into easy tutorials▲923

  https://the-pocket.github.io/Tutorial-Codebase-Knowledge/

  AI · 2025 · github.com

• 
  Whatting▲898

  The iPad diary, just for you

  Work · 2025 · whatting.com

• 
  Strawberry▲859

  Browser with AI companions that automate web tasks

  AI · 2025 · strawberrybrowser.com

• 
  Peek▲828

  AI personal finance coach that guides you through decisions

  Work · 2025 · peek.money