Skip to main content
POST
Stream Text

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
required

Audio file for streaming transcription

TargetLanguage
string
required

Language for transcription output

Example:

"ar-eg"

ModelName
enum<string>
required

Required. Speech-to-text model.

  • v1: Best Arabic quality, with strong streaming. Choose this for Arabic-only audio.
  • v2: Handles Arabic and English. Choose this when the audio mixes or switches between the two languages.
Available options:
v1,
v2
Example:

"v1"

SessionId
string

Unique session identifier

Example:

"streaming-session-1234"

SetDefaultSampleRate
enum<string>

Set to "true" to use the default sample rate. Provide this or an explicit SampleRate; transcription fails without sample-rate information.

Available options:
true,
false
Example:

"true"

SourceLanguage
string

Language of the input audio

Example:

"ar-eg"

TaskType
string

Type of processing (Transcript/Translate)

Example:

"Transcript"

OutputFormat
string

Format of the output

Example:

"Text"

RecordUrl
string<uri>

Optional. URL of an audio file to transcribe.

Example:

"https://cdn.widebot.net/tmp/audio/sample.wav"

MaxRecordLengthInSeconds
string

Maximum audio duration to process

Example:

"180"

SampleRate
string

Sample rate of the provided audio in Hz

Example:

"16000"

Response

200 - text/event-stream

Streaming transcription with progressive results

Server-sent events with transcription progress