spkrec-ecapa-voxceleb

// No extractor runs these weights, so ECAPA-TDNN runs on your side and the
// embedding is upserted through POST /v1/namespaces/{namespace_id}/documents/upsert.
// On a single-tenant deployment the other path is to upload the weights:
// 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_call_segments",
      documents: [
        {
          document_id: "call-00412-seg-07",
          // Keep the resolved speaker and the score as payload so they are
          // filterable, and store the 192-d vector so an unknown voice can be
          // matched against the gallery later.
          payload: {
            transcript: segment.text,
            speaker_id: match.speakerId,
            speaker_score: match.cosine,
            start_s: segment.start,
            end_s: segment.end,
          },
          vectors: { "speaker-embedding": ecapaEmbedding },
        },
      ],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// multimodal_extractor@v2 runs transcription over a bucket with
// run_transcription. It gives you the words without the voice identity.