Analysis
Opinion, explainers and guides from people worth reading.
VideoCan Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
An agent that hears you, sees you, and answers in your language, in real time.
These execs think voice AI hasn’t reached its ChatGPT moment yet
Voice AI's often misses important points for its context layer, and causes the whole pipeline to break
Claude Dashboards & Motion
Ask Claude for live dashboards and animated explainers
Open-source Mac app that runs EmbeddingGemma 2 locally to search your files by what’s in them
DigUp is a free Mac app that runs Google DeepMind’s new EmbeddingGemma 2 locally over your own files.
Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages
Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.
VideoHow a Voice Agent Learns the Rhythm of Conversation — Shawn Wen
Tsung-Hsien (Shawn) Wen, CTO of PolyAI, tells Tim Scarfe why voice agents are harder than text agents.
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing.
Cakie
Turn screen recordings into prompts for AI agents
PocketWebTools for Mac
Local AI chat, transcription and video tools in one Mac app
Comcent
AI-ready voice infrastructure on your own SIP trunk
VideoThe most natural voice agent was a French voice speaking English
Shawn Wen of PolyAI on why voice agents should not sound generic.
Phonable
Missed calls, handled: callers get a text, you get the gist
Foley
A voice to-do list that files, plans and asks first