SeedTTSTextTraceFlavorConfig
============================

**class** ``SeedTTSTextTraceFlavorConfig`` **(** :doc:`BaseTraceFlavorConfig` **)**

    Seed TTS eval text dataset configuration.

**Polymorphic Type:**

    ``type: seed_tts_text``

    All ``BaseTraceFlavorConfig`` types:

    - ``timed_synthetic_session``: :doc:`TimedSyntheticSessionTraceFlavorConfig`
    - ``shared_prefix``: :doc:`SharedPrefixTraceFlavorConfig`
    - ``rag``: :doc:`RAGTraceFlavorConfig`
    - ``request_log``: :doc:`RequestLogTraceFlavorConfig`
    - ``untimed_content_multi_turn``: :doc:`UntimedContentMultiTurnTraceFlavorConfig`
    - ``sharegpt``: :doc:`ShareGPTTraceFlavorConfig`
    - ``audio``: :doc:`AudioTraceFlavorConfig`
    - ``seed_tts_text``: :doc:`SeedTTSTextTraceFlavorConfig`

**Fields:**

``dataset_name`` : *str* = ``"TwinkStart/Seed-TTS-Eval"``
    Hugging Face dataset name used when local_path is empty.

``subset`` : *str* = ``"en"``
    Dataset subset/config name. Defaults to English.

``split`` : *str* = ``"train"``
    Dataset split to load.

``text_column`` : *str* = ``"text"``
    Column containing the target TTS synthesis text.

``id_column`` : *str* = ``"filename"``
    Optional source row identifier column copied into request metadata.

``local_path`` : *str* = ``""``
    Optional local dataset path. Supports saved HF datasets and common data files such as JSON/JSONL, CSV, and Parquet.

``min_tokens`` : *int* = ``20``
    Minimum input word count. Rows with fewer words are skipped. Ignored when min_chars/max_chars are set.

``max_tokens`` : *int* = ``150``
    Maximum input word count. Text is truncated to a sampled word count in [min_tokens, max_tokens]. Ignored when min_chars/max_chars are set.

``min_chars`` : *int* = ``-1``
    If >= 0, enables char-based input length control. Rows with fewer chars are skipped.

``max_chars`` : *int* = ``-1``
    If >= 0, enables char-based input length control. Text is truncated to a sampled char count in [min_chars, max_chars].