NEURA | IANUSTEC AI icon

NEURA | IANUSTEC AI

Interact with NEURA | IANUSTEC AI services using OpenAI-compatible API

Actions6

Audio → Speech

AI-generated

Summary

Converts required text to speech through the NEURA | IANUSTEC API and returns the generated audio as binary data.

Inputs

  • Model (required) — Text-to-speech model; defaults to NEURA-IANUSTEC.
  • Text Input (required) — Text to synthesize.
  • Voice — Voice to use: Alloy, Echo, Fable, Nova, Onyx, or Shimmer; defaults to Alloy.
  • Response Format — Audio format: AAC, FLAC, MP3, Opus, PCM, or WAV; defaults to MP3.
  • Speed — Speech speed from 0.25 to 4, in 0.25 increments; defaults to 1.
  • Binary Property (required) — Name of the output binary property; defaults to data.
  • Advanced Options — The UI declares options to include a raw response in JSON or save it as a named binary file, but the Speech operation returns before the shared advanced-options handling, so these options have no effect here.

Output shape

One n8n item per input item, with a JSON object and a binary audio property.

JSON contains success: true, the selected format, and the audio byte size. The binary property uses the configured name, includes the audio encoded for n8n with a MIME type based on the format, and is named speech.. API errors are thrown unless the node is configured to continue on fail.

Links

Discussion