> ## 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.

# Introduction

> A modern web UI for ElevenLabs Speech-to-Text API powered by Bun and React

# ElevenLabs Speech-to-Text API UI

A fast, modern web interface for transcribing audio and video files using the ElevenLabs Scribe API. Built with Bun, React, and Tailwind CSS, this application provides a complete playground for testing and exploring ElevenLabs' powerful speech-to-text capabilities.

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get up and running in minutes with your first transcription
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Detailed setup instructions for Bun and project dependencies
  </Card>
</CardGroup>

## Key features

This application provides a comprehensive interface for the ElevenLabs Speech-to-Text API with the following capabilities:

### Advanced transcription options

* **Multiple models** - Choose between Scribe V1 and Scribe V2
* **Speaker diarization** - Automatically detect and label different speakers in your audio
* **Timestamp granularity** - Get word-level or character-level timestamps for precise alignment
* **Multi-channel support** - Process audio files with multiple channels
* **Audio event tagging** - Detect and tag non-speech audio events

### Customization and control

* **Language detection** - Specify language codes for better accuracy
* **Custom keyterms** - Provide domain-specific terms for improved recognition
* **Entity detection** - Identify PII, PHI, or other entities in transcripts
* **Temperature control** - Fine-tune the randomness of transcription output
* **Deterministic output** - Use seed values for reproducible results

### Interactive transcript viewer

* **Synchronized playback** - Click words to jump to specific timestamps in the audio
* **Speaker labeling** - Rename speakers for better readability
* **Visual timeline** - See the full transcript with speaker segments
* **Audio scrubbing** - Navigate through your audio with a visual scrub bar

## Technology stack

This project is built with modern web technologies optimized for performance:

* **[Bun](https://bun.sh)** - All-in-one JavaScript runtime with built-in dev server and hot reload
* **[React 19](https://react.dev)** - Latest version of React for building the UI
* **[Tailwind CSS](https://tailwindcss.com)** - Utility-first CSS framework
* **[Radix UI](https://www.radix-ui.com)** - Accessible component primitives
* **[@elevenlabs/elevenlabs-js](https://www.npmjs.com/package/@elevenlabs/elevenlabs-js)** - Official ElevenLabs JavaScript SDK

## Get started

<CardGroup cols={2}>
  <Card title="Follow the quickstart" icon="circle-play" href="/quickstart">
    Learn how to transcribe your first audio file in under 5 minutes
  </Card>

  <Card title="View installation guide" icon="book-open" href="/installation">
    Complete setup instructions and verification steps
  </Card>
</CardGroup>