(AI) ElevenLabs STS icon

(AI) ElevenLabs STS

Convert speech to speech using ElevenLabs AI models

(AI) ElevenLabs STS

AI-generated

Summary

Convert speech to speech using ElevenLabs AI models, processing audio input via paths/URLs/file IDs or binary data and returning the synthesized audio response.

Inputs

  • fileModeAudio — Switch between input path/URL/File ID and binary data
  • inputPathsAudio (required) — Audio files to process • UUID (file_id): 12345678-1234-4321-abcd-123456789abc • URL: https://example.com/file.mp3 • Local path: /path/to/file.mp4
  • inputBinariesAudio (required) — Name of the Binary Properties containing the audio files. Examples: • data • image • file
  • voiceSelection (required) — Select voice by ID or by name
  • voice_id (required) — The ID of the voice to use
  • voice_name (required) — The name of the voice to use
  • model (required) — The ElevenLabs model to use for speech synthesis
  • target_format (required) — Target audio format for the output file
  • stability — Voice stability (0.0 - 1.0). Higher values make the voice more consistent
  • similarity — Voice similarity boost (0.0 - 1.0). Higher values make the voice more similar to the original
  • use_hd — Use high-definition processing for better audio quality
  • remove_background_noise — Remove background noise from the input audio
  • callback_url — Optional URL that will be called when the job is completed
  • callback_payload — Custom data that will be returned with the job completion notification

Output shape

json

API response containing the converted audio file metadata and access URL from the ElevenLabs STS service

Examples

Example 1: Process a local audio file and convert speech to speech

Set fileModeAudio to 'path', provide the local file path in inputPathsAudio, select a voice via voiceSelection/voice_id, choose a model and target format, then execute the node.

Links

Discussion