MusicGPTInstall

Summary

Transforms input audio into the selected voice, optionally removing background noise and adjusting pitch. Processing is submitted to MusicGPT, which returns task and conversion tracking details; an optional webhook URL can receive a completion notification.

Inputs

• Audio Source (required) — Choose URL (default) or Binary Property as the audio input.
• Audio URL (required) — URL of the audio to process; shown when Audio Source is URL.
• Binary Property Name (required) — Name of the incoming binary property containing the audio, usually data; shown when Audio Source is Binary Property.
• Voice Name or ID (required) — Select a voice from the available list or provide its ID with an expression.
• Remove Background — Remove background noise; defaults to false.
• Pitch — Adjust pitch from -12 to 12; defaults to 0, which leaves it unchanged.
• Webhook URL — Optional URL for a completion notification.

Output shape

One item per input item, containing a JSON object with success, task_id, conversion_id, and eta.

The operation submits the audio to MusicGPT's VoiceChanger endpoint as multipart form data. When using a binary property, the node reads its binary data and uploads it; it does not return the processed audio in this response. With Continue On Fail enabled, errors are returned in an item with an error field.

Links

• n8n community nodes installation guide