Transcribes audio into the given output format.
Derived from: EndPoint
OperationsTranscribes audio into the output format.
function : Translate(name:String, content:Byte[], model:String, token:String) ~ String
Name | Type | Description |
---|---|---|
name | String | transcription name |
content | Byte[] | byte stream to translate |
model | String | ID of the model to use |
token | String | API token |
Type | Description |
---|---|
String | translated text, Nil if unsuccessful |
Transcribes audio into the given output format.
function : Translate(name:String, content:Byte[], model:String, prompt:String, response_format:String, temperature:Float, token:String) ~ String
Name | Type | Description |
---|---|---|
name | String | transcription name |
content | Byte[] | byte stream to translate |
model | String | ID of the model to use |
prompt | String | text to guide the model's style or continue a previous audio segment |
response_format | String | format of the transcript output, options: 'json', 'text', 'srt', 'verbose_json', or 'vtt' |
temperature | Float | sampling temperature, between 0 and 1, higher values make the output more random |
token | String | API token |
Type | Description |
---|---|
String | translated text, Nil if unsuccessful |