ElevenLabs

ElevenLabs provides state-of-the-art text-to-speech and voice cloning technology. Create natural-sounding voiceovers, audiobooks, and voice assistants.

Setup

# .env
ELEVENLABS_API_KEY=...

Text-to-Speech

capabilityId: elevenlabs-tts
provider:
  type: elevenlabs
  operation: textToSpeech

inputs:
  text:
    type: string
  voiceId:
    type: string
    default: "21m00Tcm4TlvDq8ikWAM"
  modelId:
    type: string
    default: "eleven_monolingual_v1"

outputs:
  audioUrl:
    type: string
  audioData:
    type: buffer

Use cases

  • Generate voiceovers for videos
  • Create audio versions of articles
  • Build voice assistants
  • Produce audiobooks
Previous: OpenAINext: Qdrant