MusicGPTInstall

Summary

Submit audio to MusicGPT for speech transcription, using either a direct URL or binary data from an incoming item. Optionally specify the language and a callback URL; the node returns the transcription task’s status and identifiers.

Inputs

• Audio Source (required) — Choose URL (default) or Binary Property as the audio input method.
• Audio URL (required) — Direct URL of the audio file; shown when Audio Source is URL.
• Binary Property Name (required) — Name of the incoming item’s binary property containing the audio file; defaults to data and is used when Audio Source is Binary Property.
• Language — Language for transcription: auto-detect (default), Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, or Spanish. Auto Detect is omitted from the API request.
• Webhook URL — Optional URL for a completion callback.

Output shape

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

The operation submits the transcription request to MusicGPT and returns these task fields; it does not return transcription text in this response. The output item is paired with its input item. If the node is set to continue on fail, an error object is returned for the failed input.

Links

• n8n community nodes installation guide