---
title: "STTResponse"
---
STT response containing transcribed text and optional usage statistics
## Fields
| Field | Type | Required | Description | Example |
| ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `duration` | *Optional[float]* | :heavy_minus_sign: | Duration of the input audio in seconds, present when response_format is verbose_json | 9.2 |
| `language` | *Optional[str]* | :heavy_minus_sign: | Detected or forced language, present when response_format is verbose_json | english |
| `segments` | List[[components.STTSegment](../components/sttsegment.mdx)] | :heavy_minus_sign: | Timestamped transcript segments, present when response_format is verbose_json | |
| `task` | *Optional[str]* | :heavy_minus_sign: | The task performed, present when response_format is verbose_json | transcribe |
| `text` | *str* | :heavy_check_mark: | The transcribed text | Hello, this is a test of OpenAI speech-to-text transcription. The weather is sunny today and the temperature is around 72 degrees. |
| `usage` | [Optional[components.STTUsage]](../components/sttusage.mdx) | :heavy_minus_sign: | Aggregated usage statistics for the request | \{
"cost": 0.000508,
"input_tokens": 83,
"output_tokens": 30,
"seconds": 9.2,
"total_tokens": 113
} |
| `words` | List[[components.STTWord](../components/sttword.mdx)] | :heavy_minus_sign: | Timestamped words, present when the provider returns word-level timestamps | |