not much happened today

**Zyphra AI** launched **Zonos-v0.1**, a leading open-weight text-to-speech model supporting multiple languages and zero-shot voice cloning. **Meta FAIR** released the open-source **Audiobox Aesthetics** model trained on 562 hours of audio data. **Kyutai Labs** introduced **Moshi**, a real-time speech-to-speech system with low latency. **Perplexity AI** announced the **Sonar** model based on **Llama 3.3 70b**, outperforming top models like **GPT-4o** and **Claude 3.5 Sonnet** with 1200 tokens/second speed, powered by **Cerebras** infrastructure. **UC Berkeley** open-sourced a 1.5B model trained with reinforcement learning that beats **o1-preview** on math tasks. **ReasonFlux-32B** achieved 91.2% on the MATH benchmark, outperforming **OpenAI o1-preview**. **CrossPoster**, an AI agent for cross-platform posting, was released using **LlamaIndex** workflows. **Brilliant Labs** integrated the **Google DeepMind Gemini Live API** into smart glasses for real-time translation and object identification.