Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    usgvocal studio

    1

    CLI suite for voice-to-instrument synthesis, acoustic room remastering, and syllable beat-grid alignment.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    usgvocal studio

    usgvocal studio

    Example session with this skill installed

    I have a raw vocal file 'demo_vocal.wav' recorded on my phone. Can you clean it up using 'pro_reference.wav' and then align it to the beat 'track_drums.mp3' with high tightness?

    • Read your context and instructions
    • Compiled the usgvocal studio

    I have processed your audio through USGVocal Studio to clean up room reflections and lock your delivery into the pocket.

    Vocal Production Workflow

    StepCommandDescription
    Remasterpython USGvocal.py remaster --input demo_vocal.wav --reference pro_reference.wav --output clean_vocal.wavRemoves room acoustics and remaps spectral profile to match studio standard.
    Pocketpython USGvocal.py pocket --vocal clean_vocal.wav --beat track_drums.mp3 --tightness high --output final_pocketed.wavAligns syllable transients strictly to the instrumental beat grid.

    Your fully polished, radio-ready file has been saved as final_pocketed.wav!

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Recording vocals in untreated rooms or using hummed melodies as placeholders often leads to amateur results. This skill provides a specialized CLI suite to transform raw vocal tracks into professional studio assets using cross-synthesis and spectral re-mapping.

    What it does

    • Vocal-to-Instrument Synthesis converts hummed or sung melodies into brass, synth, or lead instrument tracks while keeping natural performance dynamics.
    • Acoustic Room Removal strips muddy reflections and unwanted room artifacts from raw or phone-recorded vocals.
    • Spectral Remastering matches the EQ and "air" profile of a raw vocal to a professional reference track.
    • Syllable Alignment locks vocal transients and pacing to an instrumental beat for tighter rhythmic performance.

    How it works

    1. Prepare Audio by ensuring your vocal stems and reference tracks are in WAV or MP3 format.
    2. Execute Mimic to synthesize melodic ideas into one of the supported instrument models.
    3. Run Remaster to clean up room acoustics by providing a high-quality reference file.
    4. Apply Pocketing to align the vocal timing to a specific beat with adjustable tightness levels.

    Frameworks & tools

    This tool interfaces with a Python-based CLI built on librosa, soundfile, and numpy.

    Why this beats prompting it yourself

    Generic audio prompts often result in robotic artifacts or loss of performance nuance. This skill uses specific cross-synthesis and transient-matching logic that maintains human vibrato and breath dynamics during the transformation.

    Use cases

    • Transform a hummed melody into a professional synth lead for a demo.
    • Clean up a podcast or vocal track recorded in a reverb-heavy room.
    • Align background vocals to a main instrumental track for a tighter mix.
    • Match the sonic character of a bedroom vocal to a professional studio recording.

    Known limitations

    Requires librosa and numpy installed. Limited to brass_lead, synth_pluck, and warm_lead instrument models for the mimic command.

    Requires Python dependencies (librosa, soundfile, numpy). Synthesis is limited to three specific instrument models: brass_lead, synth_pluck, and warm_lead.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    Permissions

    Terminal / Shell
    Write Files
    Read Files
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    This skill is a Python-based CLI suite that requires librosa, soundfile, and numpy. It is designed to be integrated into custom AI agent workflows or used directly via terminal on any system with a Python environment.

    The 'Remaster' feature uses spectral re-mapping to analyze the acoustic profile of a high-quality reference file and apply those characteristics to your raw recording while simultaneously stripping away room reflections.

    The 'Mimic' command currently supports three specialized instrument models: brass_lead, synth_pluck, and warm_lead, all optimized to preserve the original singer's vibrato and dynamics.

    Upon purchase, you receive the full Python CLI toolset, documentation for the Mimic, Remaster, and Pocketing commands, and the pre-trained models for vocal-to-instrument synthesis.

    Unlike generic AI audio generators, this tool uses specific transient-matching logic to ensure the vocal timing 'pockets' perfectly with your instrumental beat without losing the human feel of the performance.

    New in Agents & Orchestration