POST
Transcribe audio
Turns a clip into text. Built for Arabic as it is actually spoken (Najdi, Hijazi and Gulf) including the English product names and abbreviations that arrive in the middle of a sentence.

Sending audio

Two ways in, because a curl user and an SDK user reach for different ones.

Limits

This is the synchronous path deliberately. Longer recordings need somewhere to stage the audio, and that is handled in a deployment rather than on this endpoint.

Cost

Three cents a minute, rounded up, so a seven-second clip costs three cents. Batch a long dictation into one request rather than many short ones.

Authorizations

Authorization
string
header
required

API token from the Voho console. Begins with voho_sk_live_.

Body

Send multipart/form-data with the file attached, or JSON with the file base64 encoded.

file
file
required

The file itself. Accepted types: audio/wav, audio/x-wav, audio/mpeg, audio/mp3, audio/ogg, audio/webm, audio/flac.

language
string
default:ar-SA

BCP-47 tag for what is being spoken.

Response

The transcript.

text
string
seconds
number

Length of the audio.

confidence
number

0 to 1.

cost_cents
integer

What this call cost, in cents. Also returned as the X-Voho-Cost-Cents header.