Make your AI agent sound like it actually cares. 🎙️
I just released Emotional_Orpheus_16bit, an Orpheus-based TTS model fine-tuned on a multi-utterance, emotion-labeled dataset. It speaks in multiple characters and 26 emotions, from calm, gentle, and cheerful to anxious, whispering, and commanding.
Where it fits:
Real-time conversational chatbots and voice agents Audiobooks and storytelling Games, virtual characters and more
I have recently worked on a personal project called progressive thinking, which enables LLMs to generate chains of thought in a progressive pattern. In addition, the model learned to generate COT before choosing the appropriate tools, making it useful for complex and deeper agentic tasks. This model is well trained on QWEN3-14B using the SFT algorithm and needs GRPO to make feasible outputs. alibidaran/qwen_progressive_thinking_16bit OpenDataArena/Spark-234K IFM/TxT360-3efforts