FrankLab VOLNAInstall

Summary

Convert input text into speech audio using FrankLab VOLNA's Turbo Text to Speech endpoint, optionally waiting for processing to complete.

Inputs

• Text (required) — The text string to be converted into speech.
• Voice ID — The identifier of the voice to synthesize the speech with.
• Additional JSON — A JSON object of additional parameters to customize the FrankLab request. Media URLs must be publicly accessible via http or https.
• Wait for Completion — If true, the node will poll and wait until the speech synthesis task completes before returning the result.

Output shape

a single JSON object per input item

Each output JSON contains metadata about the synthesis task including task ID, status, cost fields, and URLs to access the generated audio (audioUrl, resultUrl, downloadUrl). If 'Wait for Completion' is enabled, output includes the final completed task result. Errors are returned in the error field if synthesis fails.

Links

• n8n community nodes installation guide