FrankLab VOLNAInstall

Summary

Convert input text to speech audio using Google's Text-to-Speech (version 3.1) engine via FrankLab VOLNA API.

Inputs

• Text (required) — The text string to convert to speech.
• Google TTS Mode (required) — Select between Single Speaker or Two Speakers mode.
• Google Voice Name (required) — Specify the Google voice name to use for synthesis.
• Speaker 1 Name — Name of the first speaker (used when mode is Two Speakers).
• Speaker 1 Voice — Voice ID or name for the first speaker (used when mode is Two Speakers).
• Speaker 2 Name — Name of the second speaker (used when mode is Two Speakers).
• Speaker 2 Voice — Voice ID or name for the second speaker (used when mode is Two Speakers).
• Style Prompt — Optional prompt to guide style or intonation of the generated speech.
• Additional JSON — Additional JSON fields to customize the FrankLab API request; media URLs must be public http/https URLs.
• Wait for Completion — Whether to wait and poll for the task completion before returning results.

Output shape

a JSON object with synthesis task details including status, task ID, and URLs to the generated audio resource.

If 'Wait for Completion' is enabled, the operation will poll until the synthesis is complete or failed and return the final task result; otherwise, it returns the immediate task creation response. The output includes fields like audioUrl and resultUrl containing the URL to access the synthesized audio.

Links

• n8n community nodes installation guide