Skip to content
HALOWERK

Textwerk

emotion de

Runs Horizon-Labs/multilingual-emotions-small locally (Apache-2.0; mmBERT-small, MIT; trained on GoEmotions, Apache-2.0, and Qwen3.8-27B translations into 35 languages incl. German; pinned revision, SHA-256 checked, int8-embedding ONNX, onnxruntime-node). Output per text: the 28 GoEmotions label probabilities (active per the label thresholds tuned on the GoEmotions validation set, thresholds.json), and six Ekman groups (anger: anger/annoyance/disapproval; fear incl. nervousness = Sorge; joy;.

POST https://text.halowerk.com/v1/emotion-de

Inputs

Fields of the published input schema
FieldTypeRequiredDescription
textsarrayYesTexts, scored one by one (together at most 5,000 model tokens).
fine_labelsstringNoWhich of the 28 GoEmotions labels to return.
Show full input schema
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "texts"
  ],
  "properties": {
    "texts": {
      "type": "array",
      "minItems": 1,
      "maxItems": 32,
      "items": {
        "type": "string",
        "minLength": 1,
        "maxLength": 4000
      },
      "description": "Texts, scored one by one (together at most 5,000 model tokens)."
    },
    "fine_labels": {
      "type": "string",
      "enum": [
        "active",
        "all",
        "none"
      ],
      "default": "active",
      "description": "Which of the 28 GoEmotions labels to return."
    }
  }
}

Open original schema

Published input example

{
  "texts": [
    "Ich bin so wütend, das Paket ist schon wieder nicht angekommen!",
    "Ich mache mir große Sorgen um meine Mutter."
  ]
}

Result & documentation

Machine-readable documentation of this hub

Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.

More endpoints in this hub

All endpoints in this hub →