NEWManaged multimodal retrieval.Explore platform →
    Models/Speech & Audio/FunAudioLLM/SenseVoiceSmall
    HFTranscription

    SenseVoiceSmall

    by FunAudioLLM

    4.0Kdl/month
    HuggingFaceUse in Pipeline
    Identifiers
    Model ID
    FunAudioLLM/SenseVoiceSmall
    Feature URI
    mixpeek://transcription@v1/alibaba_sensevoice_small_v1

    Specification

    FrameworkHF
    OrganizationFunAudioLLM
    FeatureTranscription
    Outputtext + timestamps
    Modalitiesvideo, audio
    RetrieverTranscript Search
    Downloads/mo4.0K

    Build a pipeline with SenseVoiceSmall

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Open Studio

    Alternative Models

    openai/whisper-large-v3
    Transcription
    facebook/wav2vec2-large-960h
    Transcription
    distil-whisper/distil-large-v3
    Transcription
    nvidia/parakeet-tdt-0.6b-v3
    Transcription

    Related in Speech & Audio

    pyannote/speaker-diarization-3.1
    Speaker Diarization
    pyannote/speaker-diarization-community-1
    Speaker Diarization