Skip to main content
POST
/
api
/
v1
/
AQL
/
Stream
/
SpeechToText
Stream Text
curl --request POST \
  --url https://gateway.widebot.net/api/v1/AQL/Stream/SpeechToText \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-bot: <api-key>' \
  --header 'x-user-auth: <api-key>' \
  --form Record='@example-file' \
  --form SessionId=streaming-session-1234 \
  --form SetDefaultSampleRate=true \
  --form SourceLanguage=ar-eg \
  --form TargetLanguage=ar-eg \
  --form TaskType=Transcript \
  --form OutputFormat=Text
"data: {\"partial\": \"أهلا\"}\n\ndata: {\"partial\": \"أهلا وسهلا\"}\n\ndata: {\"partial\": \"أهلا وسهلا بكم\"}\n\ndata: {\"final\": \"أهلا وسهلا بكم في تطبيقات الذكاء الاصطناعي من وايد بوت\"}\n\ndata: {\"status\": \"complete\", \"duration\": 8.5, \"consumption\": \"8/1000\"}\n"

Documentation Index

Fetch the complete documentation index at: https://doc.widebot.sa/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
x-user-auth
string
header
required

Your API key from account settings

​
x-bot
string
header
required

Your bot ID from account settings

Body

multipart/form-data
​
Record
file

Audio file for streaming transcription

​
SessionId
string

Unique session identifier

Example:

"streaming-session-1234"

​
SetDefaultSampleRate
enum<string>

Whether to use default sample rate

Available options:
true,
false
Example:

"true"

​
SourceLanguage
string

Language of the input audio

Example:

"ar-eg"

​
TargetLanguage
string

Language for transcription output

Example:

"ar-eg"

​
TaskType
string

Type of processing (Transcript/Translate)

Example:

"Transcript"

​
OutputFormat
string

Format of the output

Example:

"Text"

Response

200 - text/event-stream

Streaming transcription with progressive results

Server-sent events with transcription progress