Are FUZZ-1.0 Pro and FUZZ-1.0 the same model?
No. They are separately listed models, and FUZZ-1.0 Pro belongs to the legacy Pro tier. When making calls, explicitly specify FUZZ-1.0 Pro and avoid relying on the default selection. When comparing them, it is recommended to audition using the same lyrics and musical direction rather than judging the final result solely by the Pro name.
Do I only need a musical idea, or must I prepare complete lyrics?
You can create from a text concept or use custom lyrics. In the request structure, /riffusion/audios requires action and lyric, while /producer/audios also requires prompt; inspiration mode must also retain required fields, so you cannot directly copy simplified requests that omit fields.
How do I continue a song generated by FUZZ-1.0 Pro?
Save the song result's id, use it as audio_id in the continuation request, set action to extend, and use continue_at to specify where to continue from, in seconds. Also prepare continuation lyrics or musical direction, and audition the transition between the old and new content after completion.
Can I modify only one section of lyrics in a song?
You can use the replace_section workflow by submitting the song's audio_id, the replacement lyrics, and the time range in seconds specified by replace_section_start and replace_section_end. This regenerates the specified segment rather than replacing an existing recording word by word, so check the transitions before and after the modification.
Can a generation task finish in the background and retrieve the result later?
Yes. After setting async=true, first obtain task_id, then query the task status; you can also configure callback_url to receive the completed result. The application should save the task ID, read audio_url in data once the result is ready, and save the song ID to facilitate later covers, continuations, or partial modifications.
