This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe 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
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
voice | CUSTOM | Yes | - | Target voice for the transformation. Connect from Voice Selector or Instant Voice Clone. |
audio | AUDIO | Yes | - | Source audio to transform. |
stability | FLOAT | No | 0.0 - 1.0 | Voice stability. Lower values give broader emotional range, higher values produce more consistent but potentially monotonous speech (default: 0.5). |
model | DYNAMICCOMBO | No | eleven_multilingual_sts_v2eleven_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_format | COMBO | No | "mp3_44100_192""opus_48000_192" | Audio output format (default: “mp3_44100_192”). |
seed | INT | No | 0 - 4294967295 | Seed for reproducibility (default: 0). |
remove_background_noise | BOOLEAN | No | - | Remove background noise from input audio using audio isolation (default: False). |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
audio | AUDIO | The transformed audio file in the specified output format. |