> 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.

# Speech to Text Examples

> Production-ready code examples for Pulse STT - from real-time streaming to batch transcription.

Explore complete, runnable examples from our cookbook repository.

#### [Real-time Microphone Transcription](https://github.com/smallest-inc/cookbook/tree/main/speech-to-text/websocket/realtime-microphone-transcription)

Stream audio from your microphone over WebSocket and get real-time transcriptions.

#### [Online Meeting Notetaker](https://github.com/smallest-inc/cookbook/tree/main/speech-to-text/online-meeting-notetaking-bot)

Automatically transcribe and take notes from online meetings with speaker identification.

#### [Podcast Summarizer](https://github.com/smallest-inc/cookbook/tree/main/speech-to-text/podcast-summarizer)

Transcribe podcast episodes and generate concise summaries.

#### [Subtitle Generation](https://github.com/smallest-inc/cookbook/tree/main/speech-to-text/subtitle-generation)

Generate SRT/VTT subtitle files from audio and video content.

Browse all examples on our [GitHub repository](https://github.com/smallest-inc/cookbook/tree/main/speech-to-text).