메인 콘텐츠로 건너뛰기
ElevenLabs brings world-class voice AI to ComfyUI, covering text-to-speech, speech-to-text, sound effects, voice isolation, and voice transformation. Its Eleven v3 and Multilingual v2 models deliver emotionally expressive speech across 29 languages, while Scribe v2 provides fast, accurate transcription with speaker diarization and entity detection.

Key capabilities

  • Text to Speech — Generate lifelike audio from text with three model tiers (Eleven v3, Multilingual v2, Flash v2.5)
  • Speech to Speech — Transform a source audio clip into a different voice while keeping the original intonation and pacing
  • Speech to Text — Transcribe audio with Scribe v2: 90+ languages, 32-speaker diarization, entity detection, keyword boost
  • Sound Effects — Generate audio effects from text descriptions
  • Voice Isolation — Separate voice from background noise, music, or ambient sound
  • Multi-Character Dialogue — Generate conversations between multiple distinct voices in a single pass
파트너 노드를 사용하려면 올바르게 로그인되어 있고 허가된 네트워크 환경을 사용하고 있는지 확인해야 합니다. 파트너 노드를 사용하기 위한 구체적인 요구사항은 문서의 파트너 노드 개요 섹션을 참조해 주세요.
ComfyUI가 최신 버전으로 업데이트되었는지 확인하세요.이 가이드의 워크플로는 워크플로 템플릿에서 확인할 수 있습니다. 템플릿에서 찾을 수 없다면, 귀하의 ComfyUI가 오래된 버전일 수 있습니다.워크플로를 로드할 때 노드가 누락되는 경우, 가능한 원인:
  1. 최신 ComfyUI 버전(최신 테스트 버전(nightly))을 사용하고 있지 않음
  2. 일부 노드가 시작 시 가져오기에 실패함

Models

ElevenLabs offers a suite of specialized voice AI models, each optimized for a distinct task. From high-fidelity speech generation to real-time transcription and audio editing, the following models are available as workflow-powered nodes in ComfyUI.

Eleven Multilingual v2 / v3

High-fidelity text-to-speech with three model tiers.

Scribe v2

Fast, accurate speech-to-text with speaker diarization.

Speech to Speech

Transform audio into a different voice while preserving delivery.

Text to Sound Effects

Generate sound effects and ambient audio from text.

Text to Dialogue

Multi-character dialogue with distinct voices in one pass.

Voice Isolation

Separate voice from background noise and music.