Scaling Language-Centric Omnimodal Representation Learning Paper • 2510.11693 • Published Oct 13, 2025 • 109
WordVoice: Explicit and Decoupled Multi-Dimensional Word-Level Control for LLM-Based TTS Paper • 2607.06461 • Published 18 days ago • 1
Running on Zero MCP 11 WordVoice Word-Level Controllable TTS 🗣 11 Zero-shot TTS with explicit word-level prosody control
Running on CPU Upgrade 51 An Open Realtime Voice You Can Actually Run Yourself 📝 51 Generate real‑time spoken AI conversations
microsoft/Phi-4-multimodal-instruct Automatic Speech Recognition • 6B • Updated Dec 10, 2025 • 542k • 1.61k
SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning Paper • 2606.10804 • Published Jun 9 • 54
Preference Learning Unlocks LLMs' Psycho-Counseling Skills Paper • 2502.19731 • Published Feb 27, 2025 • 8