Represents a streamed chunk of an audio transcriptions response returned by model, based on the provided input.
data: {
"type": "transcript.text.delta",
"delta": "The"
}
data: {
"type": "transcript.text.delta",
"delta": " quick"
}
...
data: {
"type": "transcript.text.done",
"text": "The quick brown fox jumps over the lazy dog.",
"usage": {
"type": "tokens",
"input_tokens": 20,
"output_tokens": 10,
"total_tokens": 30,
"input_audio_length_ms": 18000,
"processed_audio_length_ms": 24000,
"input_token_details": {
"audio_tokens": 10,
"text_tokens": 10
}
}
}
data: [DONE]
The event type.Available options: transcript.text.delta, transcript.text.done
The incremental transcript text.
The type of the usage object. Always tokens for this variant.
Number of input tokens billed for this request.
Number of output tokens generated.
Total number of tokens used (input + output tokens).
The length of the input audio in milliseconds.
processed_audio_length_ms
The length of the processed audio in milliseconds.
Details about the input tokens billed for this request.
Number of audio tokens billed for this request.
Number of text tokens billed for this request.
