Nodes/ComfyUI/ElevenLabs Speech to Speech
ComfyUI Node Runs on cloud

ElevenLabs Speech to Speech

Transform speech from one voice to another while preserving the original content and emotion.

By Comfy-Org·Created 4 years ago·Updated 20 days ago· 121,575
ElevenLabs Speech to Speech
  • voice
  • audio
  • AUDIO
stability0.50
model
output_format
seed0
remove_background_noisefalse
Categorypartner/audio/ElevenLabs

Inputs (7)

NameTypeDefaultDescription
voiceELEVENLABS_VOICETarget voice for the transformation. Connect from Voice Selector or Instant Voice Clone.
audioAUDIOSource audio to transform.
stabilityFLOAT0.500–1Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech.
modelCOMBOModel to use for speech-to-speech transformation.
output_formatCOMBOAudio output format.
seedINT00–4294967295Seed for reproducibility.
remove_background_noiseBOOLEANfalseRemove background noise from input audio using audio isolation.

Outputs (1)

NameTypeDescription
AUDIOAUDIO