Rev.ai transcription metadata option
The metadata option is a string used to associate optional metadata with the transcription job.
AI SDK · Providers · all subjects
revai/options
23 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.
Rev.ai notification_config option
The notification_config option is an object for configuring webhook notifications when a job is complete. It contains url (string for notification URL) and auth_headers (object with optional Authorization string).
Rev.ai delete_after_seconds option
The delete_after_seconds option is an integer specifying the number of seconds after which the job will be automatically deleted.
Rev.ai verbatim option
The verbatim option is a boolean that when true includes filler words and false starts in the transcription.
Rev.ai rush option
The rush option is a boolean (HIPAA Unsupported) that when true prioritizes the job for faster processing. Only available for human transcriber option.
Rev.ai test_mode option
The test_mode option is a boolean that defaults to false. When true, runs the job in test mode.
Rev.ai segments_to_transcribe option
The segments_to_transcribe option is an array specifying specific segments of the audio to transcribe. Each segment is an object with start (number for segment start time in seconds) and end (number for segment end time in seconds).
Rev.ai speaker_names option
The speaker_names option is an array of objects for assigning names to speakers in the transcription. Each object has display_name (string for speaker display name).
Rev.ai skip_diarization option
The skip_diarization option is a boolean that defaults to false. When true, skips speaker diarization.
Rev.ai skip_postprocessing option
The skip_postprocessing option is a boolean that defaults to false. When true, skips post-processing steps. Only available for English and Spanish languages.
Rev.ai skip_punctuation option
The skip_punctuation option is a boolean that defaults to false. When true, skips adding punctuation to the transcription.
Rev.ai remove_disfluencies option
The remove_disfluencies option is a boolean that defaults to false. When true, removes disfluencies (um, uh, etc.) from the transcription.
Rev.ai remove_atmospherics option
The remove_atmospherics option is a boolean that defaults to false. When true, removes atmospheric sounds (like <laugh>, <affirmative>) from the transcription.
Rev.ai filter_profanity option
The filter_profanity option is a boolean that defaults to false. When true, filters profanity from the transcription by replacing characters with asterisks except for the first and last.
Rev.ai speakers_count option
The speakers_count option is an integer specifying the expected number of speakers in the audio. Only available for English, Spanish and French languages.
Rev.ai diarization_type option
The diarization_type option is a string specifying the type of diarization to use. Possible values are: standard (default), premium.
Rev.ai custom_vocabulary_id option
The custom_vocabulary_id option is a string specifying the ID of a custom vocabulary to use for the transcription, submitted through the Custom Vocabularies API.
Rev.ai custom_vocabularies option
The custom_vocabularies option is an array of custom vocabularies to use for the transcription.
Rev.ai strict_custom_vocabulary option
The strict_custom_vocabulary option is a boolean that when true strictly enforces custom vocabulary.
Rev.ai summarization_config option
The summarization_config option is an object for configuring a summary of the transcription. It contains model (string with values: standard (default), premium), type (string with values: paragraph (default), bullets), and prompt (string for custom prompt, mutually exclusive with type).
Rev.ai translation_config option
The translation_config option is an object for configuring translation of the transcription. It contains target_languages (array of objects with language string using codes: en, en-us, en-gb, ar, pt, pt-br, pt-pt, fr, fr-ca, es, es-es, es-la, it, ja, ko, de, ru) and model (string with values: standard (default), premium).
Rev.ai language option
The language option is a string specifying the language of the audio content as an ISO 639-1 language code. Default is en.
Rev.ai forced_alignment option
The forced_alignment option is a boolean that defaults to false. When true, performs forced alignment which provides improved accuracy for per-word timestamps. Supported languages: English (en, en-us, en-gb), French (fr), Italian (it), German (de), Spanish (es). Not available in low-cost environments.