Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The ElevenLabs Speech to Speech node transforms an input audio file from one voice to another. It uses the ElevenLabs API to convert speech while preserving the original content and emotional tone of the audio.

Inputs

ParameterData TypeRequiredRangeDescription
voiceCUSTOMYes-Target voice for the transformation. Connect from Voice Selector or Instant Voice Clone.
audioAUDIOYes-Source audio to transform.
stabilityFLOATNo0.0 - 1.0Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5).
modelDYNAMICCOMBONoeleven_multilingual_sts_v2
eleven_english_sts_v2
Model to use for speech-to-speech transformation. Each option provides a specific set of voice settings (similarity_boost, style, use_speaker_boost, speed).
output_formatCOMBONo"mp3_44100_192"
"opus_48000_192"
Audio output format (default: “mp3_44100_192”).
seedINTNo0 - 4294967295Seed for reproducibility (default: 0).
remove_background_noiseBOOLEANNo-Remove background noise from input audio using audio isolation (default: False).

Outputs

Output NameData TypeDescription
audioAUDIOThe transformed audio file in the specified output format.