StepFun AI Releases Step-Audio 2 Mini: An Open-Source 8B Speech-to-Speech AI Model that Surpasses GPT-4o-Audio Step-Audio 2 Mini, released by StepFun AI, is an open-source 8B speech-to-speech model that outperforms GPT-4o-Audio in benchmarks. Trained on 8M+ hours of multilingual audio and text data and supporting 50K+ voices, it enables expressive, emotionally aware, and real-time voice generation. With unified text-audio tokenization, on-the-fly style switching, and multimodal RAG with tool calling, Step-Audio 2 Mini sets a new standard for open audio LLMs under the Apache 2.0 license...... full analysis: marktechpost.com/2025/08/31/ste… paper: arxiv.org/abs/2507.16632 model on hugging face: huggingface.co/stepfun-ai/Ste… #Audio #tts #voiceai #LLM #LLMs #ArtificialIntelligence @StepFun_ai
Need an easy way to tail a parlay? Tag @Playbook with your book of choice and we’ll build it for you. In your reply, ride it as-is or tweak any legs ✏️ exactly how you want them.
