VibeVoice-ASR

Name: VibeVoice-ASR
Author: microsoft

by microsoft

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

8.7Bparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

microsoft/VibeVoice-ASR

Feature URI

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.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so VibeVoice-ASR runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns_your_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection_id: "col_your_collection",
      documents: [
        {
          document_id: "asset-00412",
          // The model produces text, so it lands in payload. Give the
          // collection a text vector index and embed that text to make it
          // searchable rather than only filterable.
          payload: { extracted_text: modelOutput, source_key: "archive/2026/asset-00412" },
          vectors: { "text-embedding": embeddingOfModelOutput },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// universal_extractor@v1 runs google/gemini-embedding-2
// (3072-d) over a bucket, with no inference of your own.