speaker-diarization-community-1

Name: speaker-diarization-community-1
Author: pyannote

by pyannote

Community speaker diarization pipeline for who-spoke-when audio metadata

5.1Mdl/month

1,156likes

Pipelineparams

HuggingFace Run it on your own data, free

Identifiers

Model ID

pyannote/speaker-diarization-community-1

Feature URI

mixpeek://transcription@v1/pyannote_diarization_community_1

Overview

pyannote Community-1 is a speaker diarization pipeline that segments audio by speaker turns, speech activity, speaker changes, and overlapped speech. It is publicly accessible with license acceptance and has become one of the highest-traffic diarization models on HuggingFace.

On Mixpeek, diarization turns raw audio and video transcripts into searchable conversational structure. Agents can ask not only what was said, but who said it and when it happened.

Architecture

pyannote.audio pipeline composed of voice activity detection, speaker change detection, overlapped speech detection, embedding, and clustering components. Accepts whole files or waveform excerpts.

Mixpeek SDK Integration

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so speaker-diarization-community-1 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.