NEWAgents can now see video via MCP.Try it now →
    Models/Any To Any/stepfun-ai/Step-Audio-2-mini
    Any To Anytransformersapache-2.0

    Step-Audio-2-mini

    by stepfun-ai

    2Kdl/month
    254likes
    HuggingFaceUse in Pipeline
    Identifier
    Model ID
    stepfun-ai/Step-Audio-2-mini

    Tags

    transformersonnxsafetensorsstep_audio_2text-generationany-to-anycustom_codeenzharxiv:2507.16632license:apache-2.0region:us

    Use Step-Audio-2-mini on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval, all through the Mixpeek pipeline builder.

    Open Pipeline Builder

    Specification

    Organizationstepfun-ai
    TaskAny To Any
    Librarytransformers
    Licenseapache-2.0
    Downloads/mo2K
    Likes254

    View on HuggingFace

    See model card, files, and community discussion

    Related Any To Any Models

    google/gemma-4-E4B-it
    3.5M
    OneThink/OneThinker-SFT-Qwen3-8B
    2.5M
    google/gemma-4-E2B-it
    2.5M
    Qwen/Qwen2.5-Omni-3B
    603K
    Qwen/Qwen2.5-Omni-7B
    487K
    Qwen/Qwen3-Omni-30B-A3B-Instruct
    455K
    lmstudio-community/gemma-4-E4B-it-MLX-4bit
    334K
    lmstudio-community/gemma-4-E4B-it-MLX-8bit
    319K