Skip to content

elevenlabs.mdx

Latest commit

 

History

History
58 lines (38 loc) · 2.82 KB

elevenlabs.mdx

File metadata and controls

58 lines (38 loc) · 2.82 KB
title ElevenLabs
description Convert text to speech with ElevenLabs

import { BlockInfoCard } from "@/components/ui/block-info-card"

{/* MANUAL-CONTENT-START:intro */} ElevenLabs is a state-of-the-art text-to-speech platform that creates incredibly natural and expressive AI voices. It offers some of the most realistic and emotionally nuanced synthetic voices available today, making it ideal for creating lifelike audio content.

With ElevenLabs, you can:

  • Generate natural-sounding speech: Create audio that's nearly indistinguishable from human speech
  • Choose from diverse voice options: Access a library of pre-made voices with different accents, tones, and characteristics
  • Clone voices: Create custom voices based on audio samples (with proper permissions)
  • Control speech parameters: Adjust stability, clarity, and emotional tone to fine-tune output
  • Add realistic emotions: Incorporate natural-sounding emotions like happiness, sadness, or excitement

In Sim, the ElevenLabs integration enables your agents to convert text to lifelike speech, enhancing the interactivity and engagement of your applications. This is particularly valuable for creating voice assistants, generating audio content, developing accessible applications, or building conversational interfaces that feel more human. The integration allows you to seamlessly incorporate ElevenLabs' advanced speech synthesis capabilities into your agent workflows, bridging the gap between text-based AI and natural human communication. {/* MANUAL-CONTENT-END */}

Usage Instructions

Integrate ElevenLabs into the workflow. Can convert text to speech.

Tools

elevenlabs_tts

Convert text to speech using ElevenLabs voices

Input

Parameter Type Required Description
text string Yes The text to convert to speech (e.g., "Hello, welcome to our service!")
voiceId string Yes The ID of the voice to use (e.g., "21m00Tcm4TlvDq8ikWAM" for Rachel)
modelId string No The ID of the model to use (e.g., "eleven_multilingual_v2", "eleven_turbo_v2"). Defaults to eleven_monolingual_v1
stability number No Voice stability setting from 0.0 to 1.0 (e.g., 0.5 for balanced, 0.75 for more stable). Higher values produce more consistent output
similarityBoost number No Similarity boost setting from 0.0 to 1.0 (e.g., 0.75 for natural, 1.0 for maximum similarity). Higher values make the voice more similar to the original
apiKey string Yes Your ElevenLabs API key

Output

Parameter Type Description
audioUrl string The URL of the generated audio
audioFile file The generated audio file