Mistral AI introduces Voxtral, a speech understanding model family with 24B and 3B variants under Apache 2.0. The models support long-context transcription, audio Q&A, summarization, multilingual detection, and function calling from voice. Mistral says Voxtral is competitive across transcription and audio understanding benchmarks, with API access starting at $0.001 per minute and local downloads available on Hugging Face.
Vercel's official Changelog announced that its Chat SDK has now formally incorporated AI SDK Tools functionality. This update is aimed at simplifying the often…
At Vercel's latest "Skills Night" event, the company officially announced a major update for AI Agent development: a new feature and ecosystem called "Skills,"…
### Background and Pain Points In AI agent development, "tool use" (also known as function calling) is the core capability that allows large language models…