V‑Blaze Transcription Parameters
This section describes all of the parameters that can be used in /transcribe
endpoint calls. These parameters, often referred to as stream tags, are specified using the form "name
=value
". Note that these settings are valid for a single HTTP request only. Settings for one request will not affect the transcription performed for any other requests.
Passing Parameters
Voci’s transcription service is highly configurable, enabling you to control details of how each audio file or stream is transcribed. In most cases, V‑Blaze's default behavior will provide the best results. Parameters enable you to modify default behavior when needed.
Parameter specifications must appear in the post before the audio file(s) to be transcribed. Providing a parameter setting (such as "emotion=true") after a file specification results in an error:
curl -i -F file=@sample1.wav
\ -Femotion=true
\ http://vblaze_name
:17171/transcribe
HTTP/1.1 400 Bad Request Content-Type: text/plain Content-Length: 23 Last field must be file
Make sure to always provide parameter settings before the file specification, as shown in the following example:
curl -i -Femotion=true
\ -F file=@sample1.wav
\ http://vblaze_name
:17171/transcribe