ElevenAPI

Zero Retention Mode (Enterprise)

Tools for agents to build with ElevenLabs.

This guide shows you how to reduce text-to-speech latency in your application.

Use a Pipecat pipeline as the LLM brain behind Speech Engine.

Bridge a LiveKit room into Speech Engine using a LiveKit Agents worker.

This guide shows you how to choose the right WebSocket for streaming speech and how the two protocols differ.

Stream dialogue in real-time

This guide shows you how to remix an existing voice to create a new one.

This guide shows you how to design a voice via a text prompt using the Voice Design API.

This guide shows you how to clone a voice using the Clone Voice API.

Create a dubbing project from your own transcript and supply your own translations.

Image & Video webhooks

Precise control over music generation with structured JSON

This guide shows you how to stream music with our Music API.

This guide shows you how to apply natural-language edit instructions to committed transcripts with the Realtime Speech to Text API.

This guide shows you how to handle transcripts and commit strategies with the ElevenLabs Realtime Speech to Text API.

Server-side streaming

Client-side streaming

Use the ElevenLabs Provider in the Vercel AI SDK to transcribe speech from audio and video files.

Build a Telegram bot that transcribes audio and video messages in 90+languages using TypeScript with Deno in Supabase Edge Functions.

This guide shows you how to edit transcripts with natural-language instructions using the Speech to Text API.

This guide shows you how to use entity detection with the Speech to Text API.

This guide shows you how to use keyterm prompting with the Speech to Text API.

This guide shows you how to use webhooks to receive asynchronous notifications when transcription tasks complete.

Multichannel speech-to-text

Generate and stream speech through Supabase Edge Functions. Store speech in Supabase Storage and cache responses via built-in CDN.

This guide shows you how to manage pronunciation dictionaries programmatically.

This guide shows you how to maintain voice prosody across multiple text chunks/generations.

Voice cloning: how it works

What latency means in audio generation, what contributes to it, and how to reason about tradeoffs.

Why streaming audio generation is different from streaming files, and what that means for your application.

Learn how to use the Forced Alignment API to align text to audio.

Learn how to generate sound effects using the Sound Effects API.

Learn how to dub audio and video files across languages using the Dubbing API.

Learn how to remove background noise from an audio file using the Voice Isolator API.

Learn how to transform the voice of an audio file using the Voice Changer API.

Learn how to generate immersive dialogue from text.

Learn how to convert spoken audio into text.

This guide shows you how to choose the right ElevenLabs model for your use case.