Speech-to-Text and PII removal - Part 3

speech_to_text_pii_removal.py

TRANSCRIPT_ENDPOINT = 'https://api.assemblyai.com/v2/transcript'

res_transcript = requests.post(
	TRANSCRIPT_ENDPOINT,
	headers=headers,
	json={
        'audio_url': upload_url,
        'redact_pii': True,
        'redact_pii_sub': 'entity_name',
    }, 
)
res_transcript_json = res_transcript.json()

"""
Example response from transcript endpoint
print(res_transcript_json)
{
    'id': 'w9w13r544-8459-4b06-8d7a-1e9accee4b61', 
    'language_model': 'assemblyai_default', 
    'acoustic_model': 'assemblyai_default', 
    'language_code': 'en_us', 
    'status': 'queued', 
    'audio_url': 'https://cdn.assemblyai.com/upload/4eb47686-249d-4d48-9b79-62aea715d735', 
    'text': None, 
    'words': None, 
    'utterances': None, 
    'confidence': None, 
    'audio_duration': None, 
    'punctuate': True, 
    'format_text': True, 
    'dual_channel': None, 
    'webhook_url': None, 
    'webhook_status_code': None, 
    'speed_boost': False, 
    'auto_highlights_result': None, 
    'auto_highlights': False, 
    'audio_start_from': None, 
    'audio_end_at': None, 
    'word_boost': [], 
    'boost_param': None, 
    'filter_profanity': False, 
    'redact_pii': True, 
    'redact_pii_audio': False, 
    'redact_pii_audio_quality': None, 
    'redact_pii_policies': None, 
    'redact_pii_sub': 'entity_name', 
    'speaker_labels': False, 
    'content_safety': False, 
    'iab_categories': False, 
    'content_safety_labels': {}, 
    'iab_categories_result': {}
}
"""