Edit & Polish · Versely Agent

    Separate vocals from a generated song

    One generated track. Two clean stems.

    What you say to the agent

    No special syntax — just describe it like you would to a person.

    Split that last song you made into vocal and instrumental stems
    Give me the instrumental-only version of the track we generated earlier

    What it does, step by step

    1. 1

      Reference a track generated earlier with the song-generation capability (the agent looks up its taskId/audioId from your history).

    2. 2

      It splits it into vocal and instrumental stems.

    3. 3

      You get back both stems separately.

    What it needs from you

    • The source track's task ID (from a prior Suno generation)
    • The source track's audio ID (from a prior Suno generation)

    What comes back

    Two audio files: the isolated vocal stem and the isolated instrumental stem.

    What it costs

    Priced per generation, shown before you confirm.

    Under the hood

    This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.

    separate_music_vocals

    Split a previously generated Suno track into vocal/instrumental stems. Requires the source track's taskId and audioId (from a prior generate_music / extend_music result).

    See it done in a real workflow

    Or start from a one-tap template

    Frequently asked questions

    What do I actually say to the agent to separate vocals from a generated song?+

    Just describe it in plain English — for example: "Split that last song you made into vocal and instrumental stems" The agent handles picking the right tool and model from there.

    What does the agent need from me first?+

    At minimum: The source track's task ID (from a prior Suno generation); The source track's audio ID (from a prior Suno generation). Anything else it needs, it asks for before running.

    What do I get back?+

    Two audio files: the isolated vocal stem and the isolated instrumental stem.

    Does this cost credits?+

    Priced per generation, shown before you confirm.

    You can also just ask for

    Ask your Versely agent to separate vocals from a generated song

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.