OpenAIWhisperParser#

class langchain_community.document_loaders.parsers.audio.OpenAIWhisperParser(api_key: str | None = None, *, chunk_duration_threshold: float = 0.1, base_url: str | None = None, language: str | None = None, prompt: str | None = None, response_format: Literal['json', 'text', 'srt', 'verbose_json', 'vtt'] | None = None, temperature: float | None = None, model: str = 'whisper-1')[source]#

Transcribe and parse audio files.

Audio transcription is with OpenAI Whisper model.

Parameters:

  • api_key (str | None) – OpenAI API key

  • chunk_duration_threshold (float) – Minimum duration of a chunk in seconds NOTE: According to the OpenAI API, the chunk duration should be at least 0.1 seconds. If the chunk duration is less or equal than the threshold, it will be skipped.

  • base_url (str | None)

  • language (str | None)

  • prompt (str | None)

  • response_format (Literal['json', 'text', 'srt', 'verbose_json', 'vtt'] | None)

  • temperature (float | None)

  • model (str)

Methods

__init__([api_key, ...])

lazy_parse(blob)

Lazily parse the blob.

parse(blob)

Eagerly parse the blob into a document or documents.
__init__(api_key: str | None = None, *, chunk_duration_threshold: float = 0.1, base_url: str | None = None, language: str | None = None, prompt: str | None = None, response_format: Literal['json', 'text', 'srt', 'verbose_json', 'vtt'] | None = None, temperature: float | None = None, model: str = 'whisper-1')[source]#
Parameters:

  • api_key (str | None)

  • chunk_duration_threshold (float)

  • base_url (str | None)

  • language (str | None)

  • prompt (str | None)

  • response_format (Literal['json', 'text', 'srt', 'verbose_json', 'vtt'] | None)

  • temperature (float | None)

  • model (str)

lazy_parse(blob: Blob) → Iterator[Document][source]#

Lazily parse the blob.

Parameters:

blob (Blob)

Return type:

Iterator[Document]

parse(blob: Blob) → list[Document]#

Eagerly parse the blob into a document or documents.

This is a convenience method for interactive development environment.

Production applications should favor the lazy_parse method instead.

Subclasses should generally not over-ride this parse method.

Parameters:

blob (Blob) – Blob instance

Returns:

List of documents

Return type:

list[Document]

Examples using OpenAIWhisperParser