Realtime voice, video, and AI for developers - Daily

pipecat-ai/smart-turn

Contribute to pipecat-ai/smart-turn development by creating an account on GitHub.

Pipedream Connect

Pipedream Connect provides a developer toolkit that lets you add 2,700+ integrations to your app or AI agent. Build AI apps with production-ready tools and built-in auth, ridiculously fast.

Gabber - Build Realtime AI Apps that can see, hear, and speak

Low-latency inference for VLM, TTS, and STT with orchestration for making realtime apps.

goose | Your open source AI agent

Your native open source AI agent. Desktop app, CLI, and API — for code, workflows, and everything in between.

Diving Bell Dev

We're in the business of building robust, high-quality software systems. If you like the sound of that, drop us a line.

Waterfall

The video platform giving power back to creators and their fans. Built on the AT Protocol, Waterfall lets you own your content and control your algorithms.

Realtime and audio | OpenAI API

Learn which realtime and audio guide to use for each speech application.

feathers.dev - Identity. Data. Realtime. Beyond the Cloud.

Modern web application development with secure user logins, local-first data synchronization and real-time updates. All in one place.

feathers.dev - Identity. Data. Realtime. Beyond the Cloud.

Modern web application development with secure user logins, local-first data synchronization and real-time updates. All in one place.

ICML WhisperKit: On-device Real-time ASR with Billion-Scale Transformers

Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse set of models, including a frontier model (OpenAI gpt-4o-transcribe), a proprietary model (Deepgram nova-3), and an open-source model (Fireworks large-v3-turbo).Our results show that WhisperKit matches the lowest latency at 0.46s while achieving the highest accuracy 2.2\% WER. The optimizations behind the WhisperKit system are described in detail in this paper.

Moltbook is the most interesting place on the internet right now

The hottest project in AI right now is Clawdbot, renamed to Moltbot, renamed to OpenClaw. It’s an open source implementation of the digital personal assistant pattern, built by Peter Steinberger …

Reflections: The ecosystem is moving

At Open Whisper Systems, we’ve been developing open source “consumer-facing” software for the past four years. We want to share some of the things we’ve learned while doing it. As a software developer, I envy writers, musicians, and filmmakers. Unlike software, when they create something, it is...