Enterprise: Speech to Text Transcription Endpoint
Speech To Text
Speech-to-Text allow to convert audio into written transcription in multiple languages.
POST
Enterprise: Speech to Text Transcription Endpoint
Request
Make aPOST request to below endpoint and pass the required parameters as a request body.
curl
Body
json
Body Attributes
API key for authentication.
The audio file to transcribe.
Language for the voice.
Allowed values:
Allowed values:
af, ar, be, bn, bg, zh, cs, da, nl, en, fi, fr, de, el, he, hi, hu, id, it, ja, kn, ko, ml, mr, ne, pa, fa, pl, pt, ro, ru, sr, es, sv, tl, ta, te, th, tr, uk, ur, vi, cyTimestamp level for the transcription.
Allowed values:
Allowed values:
null, word, sentenceURL to receive POST notification upon completion.
ID for webhook identification.
Whisper supports several languages, but performance may vary due to factors like limited training data, script complexity, and regional dialects, potentially affecting transcription accuracy.
Languages Supported
Body
application/json
Your API key
The audio file to transcribe
Language for the transcription
Timestamp level for the transcription
Available options:
null, word, sentence URL to receive POST notification upon completion
ID for webhook identification

