Skip to main content

​
Stream configuration template ids

​
Input data

  • multimedia content: wav, mp3, mp4, webm, flv, etc.
  • public http or https link to multimedia file encoded in UTF-8

​
Egress responses

​
Export response

​
Parameters

​
language
string | list
default:"none"
The language as country ISO code to transcribe the audio to. When not specified, it is automatically detected. When multiple languages are specified, the model will auto-detect one of the specified languages.If multiple languages are specified, the language will perform multilingual code switching between the specified languages. If none is specified, the model will switch between all supported languages.To provide multiple languages in the URL, simply add multiple language parameters. For example: language=en&language=es.
​
noSpeechThreshold
float
default:"0.5"
The threshold value to consider a segment as a speech segment. The value ranges from 0 to 1.
​
vad
bool
default:"true"
Enable or disable voice activity detection. Possible values: true or false.
​
splitStereo
bool
default:"false"
Enable or disable splitting stereo audio into two mono audio streams. Possible values: true or false.
The splitStereo parameter should not be used in this configuration
​
speakersNumber
int
default:"none"
The number of speakers to diarize the audio to. When not specified, it is automatically detected.
​
minSpeakersNumber
int
default:"none"
The minimum number of speakers to diarize the audio to.
​
maxSpeakersNumber
int
default:"none"
The maximum number of speakers to diarize the audio to.
The audio intelligence layer operates only over the transcription responses, excluding the diarization information.
​
summary
bool
default:"false"
Create a summary based on the upstream content.
​
summaryLength
string
default:"brief"
Summary length. Options are: brief or detailed.
​
summaryTone
string
default:"conversational"
Summary tone. Options are: conversational or informative.
​
summaryStructure
string
default:"paragraphs"
Summary structure. Options are: paragraphs or bullet_points.
​
sentimentAnalysis
bool
default:"false"
Perform sentiment analysis on the upstream content.
​
ask[0-N]
string
default:"none"
Specifies the custom prompt content for one of the ask0, ask1, …, askN ask anything slots. When the content is specified, the prompt is considered activated. Otherwise, it is deactivated.
​
ask[0-N]System
string
default:"none"
Specifies the custom system prompt for one of the ask0System, ask1System, …, askNSystem ask anything slots.
​
ask[0-N]Id
string
default:"none"
Specifies the prompt id for one of the ask0Id, ask1Id, …, askNId ask anything slots. The role of the prompt id is to identify the prompt in the responses. When unspecified, it will fallback on the index of the slot (e.g. "0", "1").
​
ask[0-N]Format
string
default:"none"
Specifies the prompt response JSON Schema encoded as a string for one of the ask0Format, ask1Format, …, askNFormat ask anything slots.When unspecified, the response not be structured in any particular way. When specified, the response will be a JSON object encoded as a string.
​
enhancedTranscription
bool
default:"false"
Enable transcription enhancement.
​
etModel
[standard|enhanced]
default:"standard"
Balance the speed-accuracy ration of the transcription enhancing model.
​
etVocabulary
string[]
default:"null"
Provide a list of words to enhance the transcription. Those can be domain-specific terms that the model should pay special attention to.
​
etSystemPrompt
string
default:"null"
Provide a system prompt to guide the transcription enhancement model. This can help the model understand the context or specific requirements for the transcription.
⌘I