xiry.

Development · GitHub repo

ElevenLabs NextJS Starter

Open-source Next.js boilerplate showcasing ElevenLabs audio and voice features

From the Xiry library · Updated 10 October 2026

Visit github.com ↗

An official open-source starter kit and playground by ElevenLabs built on Next.js, shadcn/ui, and Tailwind CSS v4. It gives developers pre-built interfaces and backend scaffolding for integrating text-to-speech, speech-to-text, sound effects, text-to-music, and conversational AI into web applications. It serves as an easy reference implementation for building modern AI audio tools.

What it's for

  • Bootstrap a voice-enabled web app using preconfigured ElevenLabs API routes
  • Test Eleven V3 speech generation and voice settings in an interactive playground
  • Implement speech-to-text transcription with speaker diarization and audio tagging
  • Generate custom sound effects and music tracks from text prompts

Features

  • Text to Speech and Text to Dialogue powered by Eleven V3 preview models
  • Speech to Text transcription using ElevenLabs models like scribe_v1
  • Text-driven sound effect generator
  • Text to Music generator with composition planning support
  • Conversational AI interface setup
  • Pre-styled UI components using shadcn/ui and Tailwind CSS v4
  • Secure server-side API key handling using iron-session

Pricing

Open source. Free and open source (MIT license); requires an ElevenLabs API key (usage billed by ElevenLabs)

Details

Type
GitHub repo
Category
Development
Topic
Boilerplates & Starters
Open source
Yes
Platforms
Web
For
Next.js and React developers building voice or audio AI features
Tags
nextjs, elevenlabs, audio, text to speech, speech to text, react, shadcn

Why it was saved

  • @ElevenLabsDevs, 7 May 2025: Ready-made codebase for shipping AI audio features quickly; uses ElevenLabs SDK (incl. V3 expressive model), Next.js + shadcn/ui, Tailwind CSS v4.

Related

All 6 in Boilerplates & Starters →

Updated