BUNDLE Security scanned3 skills

    NOVA Voice Agent Starter Kit

    Everything an AI agent needs to work by voice, from Nova, an open-source voice assistant built on Claude Code and Codex. The three skills cover the three jobs of a voice agent: hearing, speaking and acting safely.

    nova-hinglish-stt sets up offline speech-to-text for English, Hindi and Hinglish, with Hindi written in Roman letters.
    voice-replies makes the agent answer in one short spoken line, with the details kept on screen.
    voice-agent-guard is a rulebook for a permission hook that decides which commands run, which ask first and which never run.

    For developers building a voice assistant or a hands-free agent on Claude Code, Codex or a similar tool. On its own, each skill solves one piece. Together they cover the full loop: the user speaks, the agent acts within safe limits, and it answers in a way that sounds right out loud. The listening, speaking and microphone parts of your app are still yours to build.

    Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.

    Ayush Mishra
    Created by
    Ayush Mishra
    $10.50$15
    Save 30% · $4.50

    One payment, lifetime access. 3 skills unlock instantly in your library.

    Money-back guarantee

    Instant unlock in your library

    Free updates from the creator

    What's included

    3 skills

    See it in action

    NOVA Hinglish STT

    NOVA Hinglish STT

    Example session with this skill installed

    I need a Python script to transcribe 'audio_input.wav' which contains a mix of Hindi and English. It must output the Hindi parts in Roman script.

    • Read your context and instructions
    • Compiled the nova hinglish stt

    I have configured the transcription script using the Nova Whisper Hinglish model. This setup includes Voice Activity Detection (VAD) to handle silence and uses float16 compute for GPU efficiency.

    Hinglish Transcription Script

    import os
    import sys
    from faster_whisper import WhisperModel
    
    # Ensure CUDA DLLs are in path for Windows GPU usage
    # os.environ["PATH"] = r".venv\Lib\site-packages\nvidia\cublas\bin;" + os.environ["PATH"]
    
    def transcribe_hinglish(audio_path):
        # Initialize model on GPU with float16 for speed
        model = WhisperModel(
            "AyushM1701/nova-whisper-hinglish", 
            device="cuda", 
            compute_type="float16"
        )
    
        # Custom VAD to avoid clipping soft word endings
        vad_params = {
            "threshold": 0.35,
            "speech_pad_ms": 300,
            "min_silence_duration_ms": 500
        }
    
        # language="hi" forces Romanized Hindi output
        segments, info = model.transcribe(
            audio_path,
            language="hi",
            vad_filter=True,
            vad_parameters=vad_params,
            beam_size=1,
            condition_on_previous_text=False
        )
    
        return " ".join(s.text.strip() for s in segments)
    
    if __name__ == "__main__":
        result = transcribe_hinglish("audio_input.wav")
        print(f"Transcription: {result}")
    

    Next steps

    • Install dependencies using pip install faster-whisper "av<16".
    • If running on Windows with a GPU, verify the CUDA 12 bin folders are added to your environment PATH.
    • Run the script; the first execution will download the 1.6 GB model weights.

    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 these skills and uses them on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every skill in this bundle goes through our trust checks.

    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.

    Frequently asked questions

    Yes — every skill in NOVA Voice Agent Starter Kit is also sold on its own product page. The bundle just packages them together at a discount (save 30% vs buying each one separately).

    Yes. When you own the bundle your connected agent can load the latest version of any included skill. Updates the creator publishes after your purchase are included at no extra cost.

    All skills in this bundle use the open SKILL.md standard and work with Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf. The compatibility list on this page is computed from the included skills.

    The bundle price is set 30% below the combined retail price of the 3 paid skills included. You pay once and unlock every skill in your library instantly.

    Bundles are covered by the same money-back guarantee as individual skills. Doesn't do what its page promises? You get your money back.

    No. The skills tell your agent how to transcribe audio, how to write replies for speech, and which commands are safe. Recording, playing speech and opening the mic are up to your app.

    No. The speech model runs on a CPU, at about a second or more per clip. An NVIDIA GPU makes it much faster. The other two skills need nothing installed.

    The reply and guard skills work in any agent. The speech skill needs an agent that runs on your own computer, such as Claude Code, Codex or Cursor, because it installs Python packages and downloads a 1.6 GB model.