> ## Documentation Index
> Fetch the complete documentation index at: https://openrouter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# STTSegment

A timestamped transcript segment, returned when response\_format is verbose\_json

## Example Usage

```typescript theme={null}
import { STTSegment } from "@openrouter/sdk/models";

let value: STTSegment = {
  end: 3.2,
  id: 0,
  start: 0,
  text: "Hello there.",
};
```

## Fields

| Field | Type | Required | Description | Example |
| - | - | - | - | - |
| `avgLogprob` | *number* | ➖ | Average log probability of the segment | |
| `channel` | *number* | ➖ | Zero-based audio channel index for the segment, present when the provider transcribes channels separately | 0 |
| `compressionRatio` | *number* | ➖ | Compression ratio of the segment | |
| `end` | *number* | ✅ | Segment end time in seconds | 3.2 |
| `id` | *number* | ✅ | Segment index within the transcript | 0 |
| `noSpeechProb` | *number* | ➖ | Probability the segment contains no speech | |
| `seek` | *number* | ➖ | Seek offset of the segment | 0 |
| `speaker` | *number* | ➖ | Speaker index for the segment, present when the provider returns diarization data | 0 |
| `speakerLabel` | *string* | ➖ | Provider speaker label for the segment, present when the provider labels speakers with a string | speaker\_0 |
| `start` | *number* | ✅ | Segment start time in seconds | 0 |
| `temperature` | *number* | ➖ | Temperature used for the segment | |
| `text` | *string* | ✅ | Transcribed text of the segment | Hello there. |
| `tokens` | *number*\[] | ➖ | Token IDs of the segment | |