> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Features

> Available features for Pre-Recorded Pulse STT API

The Pre-Recorded Pulse STT API supports the following features:

## Available Features

#### [Word Timestamps](/models/documentation/speech-to-text-pulse/features/word-timestamps)

Get precise timing information for each word in the transcription

#### [Language Detection](/models/documentation/speech-to-text-pulse/features/language-detection)

Automatically detect the language of the audio

#### [Diarization](/models/documentation/speech-to-text-pulse/features/diarization)

Identify and label different speakers in the audio

#### [Gender Detection](/models/documentation/speech-to-text-pulse/features/gender-detection)

Predict speaker gender alongside transcription

#### [Emotion Detection](/models/documentation/speech-to-text-pulse/features/emotion-detection)

Detect emotional tone in the transcribed speech

#### [Redaction](/models/documentation/speech-to-text-pulse/features/redaction)

Automatically redact sensitive information from transcriptions

#### [Utterances](/models/documentation/speech-to-text-pulse/features/utterances)

Segment transcription into meaningful utterances (requires word\_timestamps)

**Keyword Boosting** is available on the [Real-Time WebSocket API](/models/documentation/speech-to-text-pulse/realtime-web-socket/features) only. It is not supported on the pre-recorded HTTP endpoint.