NEWVectors or files. Pick a path.Start →
    Models/Automatic Speech Recognition/microsoft/VibeVoice-ASR

    VibeVoice-ASR

    by microsoft

    Speech recognition with diarization in one model, at 8.7B parameters

    Identifier
    Model ID
    microsoft/VibeVoice-ASR

    Overview

    Most transcription stacks run two models: one to turn audio into words, another to work out who was speaking. VibeVoice-ASR declares both, which removes an alignment step that is a common source of quiet errors when the two models disagree about segment boundaries.

    At 8.7B parameters this is a large model and belongs on interviews, meetings and panel content where knowing the speaker changes what the transcript is worth. For bulk single-speaker material a smaller model will cost far less per hour and lose nothing you need.

    MIT licensed.

    Architecture

    VibeVoiceForASRTraining, 8,674,021,857 parameters. Automatic-speech-recognition pipeline with diarization declared on the model card.

    Key Capabilities

    • Transcription and speaker diarization from one model
    • Speaker-attributed transcripts without a separate alignment step
    • English declared on the card
    • MIT licence, so self-hosting carries no usage restriction

    Use Cases on Mixpeek

    • Interview and meeting archives where who-said-it is the searchable part
    • Panel and podcast content with overlapping speakers
    • Building a per-speaker index rather than a per-file one
    • Replacing a two-model transcribe-then-diarize pipeline

    Tags

    transformerssafetensorsvibevoiceASRTranscriptoinDiarizationSpeech-to-Textautomatic-speech-recognitionenzhesptdejakofrruidsvithenlplnotrtharhucacs

    Use VibeVoice-ASR on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, VibeVoice-ASR runs as a managed extractor inside a processing pipeline. Point a bucket of automatic speech recognition data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.