get_medical_transcription_job
Get Medical Transcription Job
Retrieve status and details for a medical transcription job, including transcript URI, specialty, type, and failure details.
get_medical_transcription_job
Retrieve status and details for a medical transcription job, including transcript URI, specialty, type, and failure details.
delete_transcription_job
Delete a transcription job and its associated metadata. The job must be in a terminal state (COMPLETED or FAILED) to be deleted. This does not delete the transcript output from S3.
manage_vocabulary
Create, update, get, delete, or list custom vocabularies. Custom vocabularies improve transcription accuracy for domain-specific words like product names, technical terms, or proper nouns. Provide terms as a list of phrases or via an S3 file.
manage_vocabulary_filter
Create, update, get, delete, or list vocabulary filters. Vocabulary filters specify words to remove, mask, or tag in transcripts — commonly used for removing profanity or unwanted words. Provide filter words as a list or via an S3 file.
list_call_analytics_jobs
List Call Analytics jobs in your AWS account. Filter by job status or job name and paginate through results.
start_transcription_job
Start a batch transcription job to convert speech from an audio or video file stored in Amazon S3 to text. Supports features like speaker diarization, channel identification, custom vocabularies, PII redaction, subtitle generation, and toxicity detection. The job runs asynchronously; use **Get Transcription Job** to check status and retrieve results.
delete_medical_transcription_job
Delete a medical transcription job and its metadata. This does not delete transcript output stored in S3.
list_language_models
List custom language models in your AWS account. Filter by status or name to find specific models. Custom language models improve transcription accuracy for specific domains by training on your text data.
delete_call_analytics_job
Delete a Call Analytics job and its metadata. This does not delete transcript output stored in S3.
start_medical_transcription_job
Start a medical transcription job to convert medical speech to text. Incorporates medical terminology for use cases like transcribing doctor-patient dialogue, physician notes, and dictation. Supports speaker diarization and channel identification for multi-party conversations.
list_transcription_jobs
List transcription jobs in your AWS account. Filter by status or job name to find specific jobs. Returns summaries with job names, statuses, creation times, and language codes. Supports pagination for large result sets.
manage_medical_vocabulary
Create, update, get, delete, or list custom medical vocabularies for Amazon Transcribe Medical. Medical vocabularies use a vocabulary table file stored in S3 or an accessible URI.
get_transcription_job
Retrieve the status and details of a transcription job including its transcript output URI, language, settings, and completion time. Use this to check if a job has completed and to get the transcript location.
start_call_analytics_job
Start a Call Analytics transcription job that processes call center audio to extract insights like sentiment, call categories, characteristics, and AI-powered summaries. Designed for two-channel audio where agent and customer are on separate channels. Can also redact PII from both transcripts and source audio.
manage_call_analytics_category
Create, update, get, delete, or list Call Analytics categories. Categories define rule-based labels that AWS applies to Call Analytics jobs created after the category exists.
list_medical_transcription_jobs
List medical transcription jobs in your AWS account. Filter by status or job name and paginate through results.
get_call_analytics_job
Retrieve the status and details of a Call Analytics job including transcript URIs, channel definitions, completion time, and failure reason. Use this to check if a call analytics job has completed and to get the results location.
Transcribe speech to text from audio and video files or real-time audio streams. Perform batch transcription of media files stored in S3 and streaming transcription of live audio. Automatically identify languages, apply custom vocabularies and language models, filter unwanted words, identify speakers (diarization), and transcribe multi-channel audio. Redact personally identifiable information (PII) from transcripts. Generate subtitles in WebVTT and SRT formats. Detect toxic speech content. Analyze call center audio to extract sentiment, call categories, and AI-powered summaries. Transcribe medical dictation and patient-clinician conversations. Generate clinical notes from healthcare conversations using AWS HealthScribe. Monitor transcription job state changes, language identification events, and vocabulary updates via EventBridge.
Common questions about connecting Aws Transcribe to AI agents with Metorial.