FrankLab VOLNA icon

FrankLab VOLNA

Generate and process speech, voice, dubbing, and audio with FrankLab VOLNA.

Actions16

Speech → Text to Speech

AI-generated

Summary

Convert input text to synthetic speech audio using the FrankLab VOLNA text-to-speech service.

Inputs

  • Text (required) — The text content to be converted into speech.
  • Voice ID — Optional identifier for the voice to use for synthesis.
  • Additional JSON — Optional JSON object to specify additional request fields supported by the FrankLab API. Media URLs in this JSON must be public HTTP or HTTPS URLs.
  • Wait for Completion — Boolean flag to determine if the operation should wait and poll for the completion status of the speech generation task before returning results.

Output shape

A single record containing synthesis results including audio URLs, task ID, status, cost details, and any potential errors.

If 'Wait for Completion' is true, the node will poll until the speech synthesis task finishes or fails, returning final results. The output includes fields such as 'audioUrl' and 'resultUrl' for accessing the generated audio media.

Examples

Example 1: Generate spoken audio from text using a specific voice and wait for completion.

Set 'Text' to input text, optionally set 'Voice ID', and enable 'Wait for Completion'. The node returns the audio URL and synthesis task status once completed.

Links

Discussion