🎧💻 Meet Step-Audio-EditX! An open-source audio model by Stepan (Stepfun) powered by a 3B parameter LLM. Get ready for expressive and iterative sound editing that’s as easy as pie! 🥧 Imagine generating speech from text without any extra training. 🤯 It’s like magic! ✨ Check out these cool features: - Clean up audio noise 🎶 - Speed up speech ⏩ - Change emotions in voices 😄➡️😢 - Transform regular speech into whispers 🤫 - Control 10 types of paralinguistic features, like breath, laughter, sighs, and more! 😮💨😂 Supports both Chinese & English 🇨🇳🇺🇸, operates at 41.6Hz, and needs 32GB of VRAM for an optimal experience with audio lengths of up to 30 seconds. Let’s elevate our audio game! 🔊✨ #AudioEditing #Innovation
🎧💻 Meet Step-Audio-EditX! An open-source audio model by Stepan (Stepfun) powered by a 3B parameter LLM. Get ready for expressive and iterative sound editing that’s as easy as pie! 🥧
Imagine generating speech from text without any extra training. 🤯 It’s like magic! ✨
Check out these cool features:
- Clean up audio noise 🎶
- Speed up speech ⏩
- Change emotions in voices 😄➡️😢
- Transform regular speech into whispers 🤫
- Control 10 types of paralinguistic features, like breath, laughter, sighs, and more! 😮💨😂
Supports both Chinese & English 🇨🇳🇺🇸, operates at 41.6Hz, and needs 32GB of VRAM for an optimal experience with audio lengths of up to 30 seconds.
Let’s elevate our audio game! 🔊✨ #AudioEditing #Innovation
