> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/konhi/elevenlabs-speech-to-text-api-ui/llms.txt
> Use this file to discover all available pages before exploring further.

# Transcription Options

> Configure model selection, language, timestamps, and speaker detection for accurate transcriptions

## Overview

The Speech-to-Text Playground provides comprehensive transcription configuration options. All options are part of the `TranscriptOptions` interface defined in `speech-to-text-types.ts`:

```typescript theme={null}
export type TranscriptOptions = {
  modelId: "scribe_v1" | "scribe_v2";
  languageCode?: string;
  tagAudioEvents: boolean;
  numSpeakers?: number;
  timestampsGranularity: "none" | "word" | "character";
  diarize: boolean;
  diarizationThreshold?: number;
  temperature?: number;
  seed?: number;
  useMultiChannel: boolean;
  keyterms?: string[];
  entityDetection?: string;
};
```

## Default Configuration

The playground uses these default values:

```tsx theme={null}
const defaultTranscriptOptions: TranscriptOptions = {
  modelId: "scribe_v2",
  tagAudioEvents: false,
  timestampsGranularity: "character",
  diarize: false,
  useMultiChannel: false,
};
```

## Core Options

### Model Selection

<ParamField path="modelId" type="'scribe_v1' | 'scribe_v2'" default="scribe_v2" required>
  The Scribe model version to use for transcription.

  * **scribe\_v1**: First generation model, stable and reliable
  * **scribe\_v2**: Latest model with improved accuracy and features (recommended)
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Select value={options.modelId} onValueChange={handleModelChange}>
  <SelectTrigger id="model">
    <SelectValue />
  </SelectTrigger>
  <SelectContent>
    <SelectItem value="scribe_v1">Scribe V1</SelectItem>
    <SelectItem value="scribe_v2">Scribe V2</SelectItem>
  </SelectContent>
</Select>
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  modelId: options.modelId || "scribe_v2",
  // ... other options
});
```

### Language Code

<ParamField path="languageCode" type="string" default="undefined">
  Optional ISO language code to improve transcription accuracy for specific languages.

  Examples: `"en"`, `"es"`, `"fr"`, `"de"`, `"ja"`, `"zh"`

  When not specified, the model will attempt to auto-detect the language.
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Input
  id="language"
  placeholder="e.g., en, es, fr"
  value={options.languageCode || ""}
  onChange={handleLanguageChange}
/>
```

**Implementation:**

```tsx theme={null}
function handleLanguageChange(event: ChangeEvent<HTMLInputElement>) {
  const value = event.target.value || undefined;
  onOptionsChange({ ...options, languageCode: value });
}
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  languageCode: options.languageCode || undefined,
  // ... other options
});
```

### Tag Audio Events

<ParamField path="tagAudioEvents" type="boolean" default="false">
  When enabled, the transcript will include tags for non-speech audio events such as laughter, applause, music, or background noise.
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Checkbox
  id="tagAudio"
  checked={options.tagAudioEvents}
  onCheckedChange={handleTagAudioChange}
/>
<Label htmlFor="tagAudio">Tag Audio Events</Label>
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  tagAudioEvents: options.tagAudioEvents || false,
  // ... other options
});
```

## Timestamp Options

### Timestamps Granularity

<ParamField path="timestampsGranularity" type="'none' | 'word' | 'character'" default="character" required>
  Controls the level of detail for timestamp information in the transcription.

  * **none**: No timestamps included
  * **word**: Timestamps for each word
  * **character**: Timestamps for each character (most detailed)
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Select
  value={options.timestampsGranularity}
  onValueChange={handleTimestampsChange}
>
  <SelectTrigger id="timestamps">
    <SelectValue />
  </SelectTrigger>
  <SelectContent>
    <SelectItem value="none">None</SelectItem>
    <SelectItem value="word">Word</SelectItem>
    <SelectItem value="character">Character</SelectItem>
  </SelectContent>
</Select>
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  timestampsGranularity: options.timestampsGranularity || "character",
  // ... other options
});
```

<Info>
  Character-level timestamps enable precise synchronization with audio playback and detailed alignment visualization in the transcript viewer.
</Info>

## Speaker Detection (Diarization)

### Diarize

<ParamField path="diarize" type="boolean" default="false">
  Enable speaker diarization to identify and separate different speakers in the audio.

  When enabled, the transcript will include speaker labels (e.g., Speaker 1, Speaker 2) to distinguish between different voices.
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Checkbox
  id="diarize"
  checked={options.diarize}
  onCheckedChange={handleDiarizeChange}
/>
<Label htmlFor="diarize">Diarize (Speaker Detection)</Label>
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  diarize: options.diarize || false,
  // ... other options
});
```

### Number of Speakers

<ParamField path="numSpeakers" type="number" default="undefined">
  Specify the expected number of speakers in the audio (1-32).

  When not specified, the model will attempt to auto-detect the number of speakers.

  Providing an accurate count can improve diarization accuracy.
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Input
  id="speakers"
  type="number"
  min="1"
  max="32"
  placeholder="Auto-detect"
  value={options.numSpeakers || ""}
  onChange={handleNumSpeakersChange}
/>
```

**Implementation:**

```tsx theme={null}
function handleNumSpeakersChange(event: ChangeEvent<HTMLInputElement>) {
  const value = event.target.value;
  const numSpeakers = value ? parseInt(value, 10) : undefined;
  onOptionsChange({ ...options, numSpeakers });
}
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  numSpeakers: options.numSpeakers || undefined,
  // ... other options
});
```

### Diarization Threshold

<ParamField path="diarizationThreshold" type="number" default="undefined">
  Fine-tune the sensitivity of speaker detection (0.0-1.0).

  * **Lower values** (closer to 0): More sensitive, may create more speaker segments
  * **Higher values** (closer to 1): Less sensitive, may merge speakers together

  Only applies when `diarize` is `true` and `numSpeakers` is not specified.
</ParamField>

**Usage in UI:**

```tsx theme={null}
{options.diarize && !options.numSpeakers && (
  <div className="space-y-2">
    <Label htmlFor="diarization-threshold">
      Diarization Threshold (0.0-1.0)
    </Label>
    <Input
      id="diarization-threshold"
      type="number"
      step="0.01"
      min="0"
      max="1"
      placeholder="Auto"
      value={options.diarizationThreshold || ""}
      onChange={handleDiarizationThresholdChange}
    />
  </div>
)}
```

**Implementation:**

```tsx theme={null}
function handleDiarizationThresholdChange(event: ChangeEvent<HTMLInputElement>) {
  const value = event.target.value;
  const diarizationThreshold = value ? parseFloat(value) : undefined;
  onOptionsChange({ ...options, diarizationThreshold });
}
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  diarizationThreshold: options.diarizationThreshold || undefined,
  // ... other options
});
```

<Note>
  The diarization threshold field only appears in the UI when diarization is enabled and the number of speakers is not explicitly set.
</Note>

## Multi-Channel Audio

### Use Multi-Channel

<ParamField path="useMultiChannel" type="boolean" default="false">
  Enable multi-channel processing for audio files with multiple channels (e.g., stereo recordings where each speaker is on a separate channel).

  When enabled, each audio channel is processed separately, which can improve accuracy for multi-channel recordings.
</ParamField>

**Usage in UI:**

```tsx theme={null}
<Checkbox
  id="multichannel"
  checked={options.useMultiChannel}
  onCheckedChange={handleMultiChannelChange}
/>
<Label htmlFor="multichannel">Multi-channel Audio</Label>
```

**API Call:**

```tsx theme={null}
await browserClient.speechToText.convert({
  useMultiChannel: options.useMultiChannel || false,
  // ... other options
});
```

<Tip>
  Use multi-channel processing when you have recordings where each speaker is isolated to a specific audio channel, such as professional podcast recordings or call center recordings.
</Tip>

## Common Configurations

<AccordionGroup>
  <Accordion title="Podcast Transcription">
    Recommended settings for podcast transcription:

    ```tsx theme={null}
    {
      modelId: "scribe_v2",
      languageCode: "en",
      tagAudioEvents: true,
      numSpeakers: 2, // or the actual number of hosts
      timestampsGranularity: "word",
      diarize: true,
      useMultiChannel: true // if each host is on a separate channel
    }
    ```
  </Accordion>

  <Accordion title="Interview Transcription">
    Recommended settings for interview transcription:

    ```tsx theme={null}
    {
      modelId: "scribe_v2",
      languageCode: "en",
      tagAudioEvents: false,
      numSpeakers: 2,
      timestampsGranularity: "character",
      diarize: true,
      useMultiChannel: false
    }
    ```
  </Accordion>

  <Accordion title="Meeting Transcription">
    Recommended settings for meeting transcription:

    ```tsx theme={null}
    {
      modelId: "scribe_v2",
      languageCode: "en",
      tagAudioEvents: true,
      // numSpeakers: undefined (auto-detect)
      timestampsGranularity: "word",
      diarize: true,
      diarizationThreshold: 0.5,
      useMultiChannel: false
    }
    ```
  </Accordion>

  <Accordion title="Quick Transcription (No Speaker Info)">
    Fastest transcription without speaker detection:

    ```tsx theme={null}
    {
      modelId: "scribe_v2",
      tagAudioEvents: false,
      timestampsGranularity: "none",
      diarize: false,
      useMultiChannel: false
    }
    ```
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Advanced Settings" icon="gears" href="/configuration/advanced-settings">
    Configure keyterms, entity detection, temperature, and seed
  </Card>

  <Card title="Using the Transcript" icon="file-lines" href="/features/transcript-viewer">
    Learn how to view and interact with your transcriptions
  </Card>
</CardGroup>