Step-Audio model family, including Audio-Tokenizer, Audio-Chat and TTS
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Welcome to StepFun 🙋
StepFun, founded in April 2023 with the mission to “Scale-up possibilities for everyone,” unites top talent in artificial intelligence from both domestic and international backgrounds, and is dedicated to advancing toward AGI. The company has already launched the Step series of foundation models, which includes Step-2, a cutting-edge trillion-parameter Mixture of Experts (MoE) language model; Step-1.5V, a powerful multimodal large model; and Step-1V, an innovative image generation model, among others.
Our discord channel here:https://discord.gg/92ye5tjg7K, join us to create AI future together!
models
12
stepfun-ai/Step1X-Edit
Image-to-Image
•
Updated
•
748
•
•
294
stepfun-ai/Step-Audio-AQAA
137B
•
Updated
•
90
•
29
stepfun-ai/Qwen2.5-32B-DialogueReason
33B
•
Updated
•
27
•
12
stepfun-ai/Step1X-3D
Updated
•
90
stepfun-ai/stepvideo-ti2v
Image-to-Video
•
Updated
•
122
•
82
stepfun-ai/stepvideo-t2v
Text-to-Video
•
Updated
•
447
•
467
stepfun-ai/Step-Audio-Tokenizer
Updated
•
38
stepfun-ai/Step-Audio-Chat
Audio-Text-to-Text
•
132B
•
Updated
•
115
•
445
stepfun-ai/Step-Audio-TTS-3B
Text-to-Speech
•
4B
•
Updated
•
171
•
•
187
stepfun-ai/stepvideo-t2v-turbo
Updated
•
94