SunoInstall

Summary

Add vocals to an uploaded audio file by providing a descriptive generation prompt, style tags, and metadata for a title and optional vocal gender, along with control parameters such as style weight, weirdness constraint, audio weight, and model version. The operation requires an HTTPS URL of the uploaded audio to augment.

Inputs

• Upload URL (required) — HTTPS URL of the uploaded audio file (max 8 minutes; private IPs rejected).
• Prompt (required) — Text prompt describing the desired vocals to generate.
• Title (required) — Title for the generated track (max 100 characters).
• Style (required) — Music style tags describing the vocal generation.
• Negative Tags (required) — Music styles or traits to exclude from the generated track.
• Callback URL (required) — HTTPS URL to receive task completion notifications; must be publicly accessible and not point to private IPs.
• Vocal Gender — Preferred vocal gender for the generated track (Male or Female).
• Style Weight — Numeric value (0.00-1.00) controlling style influence strength.
• Weirdness Constraint — Numeric value (0.00-1.00) limiting creative deviation.
• Audio Weight — Numeric value (0.00-1.00) determining input audio influence.
• Model (required) — The AI model version to use for generation (V4.5 Plus or V5).

Output shape

a JSON object containing the API response data for the vocal addition task

The response includes details about the vocal generation task initiated by the provided parameters. The provided Callback URL will receive task completion notifications.

Links

• n8n community nodes installation guide