More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    NOVA Hinglish STT

    1

    Speech-to-text for English and Hinglish that outputs Romanized Hindi instead of Devanagari using faster-whisper.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    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.

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

    About this skill

    Standard Whisper models fail on Hinglish, outputting messy Devanagari or hallucinating translations. This skill implements Nova Whisper Hinglish to provide transcription that writes Hindi in Roman letters, exactly as users type it.

    What it does

    • Romanized Hindi output ensures "kal meeting cancel kar do" stays in Roman script rather than Devanagari.
    • Multilingual switching detects English or Hindi for each clip, so users can switch languages from one sentence to the next.
    • Optimized performance uses CTranslate2 via faster-whisper for high-speed inference on CPU or GPU.
    • Voice activity detection applies custom VAD parameters to trim silence without clipping soft word endings.
    • Offline execution runs entirely on local hardware after the initial model download.

    How it works

    1. Environment setup creates a virtual environment and pins specific library versions like av<16 to prevent runtime crashes.
    2. Model initialization loads the 1.6 GB nova-whisper-hinglish weights with optimized compute types like int8 or float16.
    3. Language detection analyzes audio clips to choose between en or hi modes before processing.
    4. Transcription processes an audio file or array with the silence filter on and condition_on_previous_text=False, so one bad segment can’t repeat through the rest.

    Frameworks & tools

    This skill uses Python, faster-whisper, CTranslate2, and NVIDIA CUDA 12 libraries. It specifically utilizes the AyushM1701/nova-whisper-hinglish model from Hugging Face.

    Why this beats prompting it yourself: Prompting an LLM to romanize a Devanagari transcript adds latency and token costs. This skill fixes it in the model weights: on the MUCS 2021 Hinglish test set it makes about 40% fewer word errors than stock Whisper large-v3-turbo (45.7% vs 77.9%, after converting stock Whisper’s Devanagari output to Roman letters), at the same speed.

    Use cases

    • Message dictation for apps where users prefer typing Hindi in the Roman alphabet.
    • Customer support analysis for Indian markets where Hinglish is the primary spoken dialect.
    • Meeting transcription for bilingual teams switching frequently between English and Hindi.
    • Voice commands for IoT devices or local bots in the Indian subcontinent.

    Known limitations

    Needs about 2 GB of disk space and Python 3.9+. CPU only on Mac, so expect about a second or more per clip. On a Windows GPU, the CUDA bin folders must be on the PATH of the terminal that runs it. The model is licensed CC BY-SA 4.0. The Hinglish test clips come from the same corpus as most of the training data, so expect a smaller gain on other Hinglish.

    Requires 2GB disk space. Python 3.9+ required. Windows GPU usage requires manual PATH configuration for CUDA DLLs. Only supports Romanized script for Hindi, not Devanagari.

    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 5 days ago

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    Standard Whisper models often force Hindi into Devanagari script or mistranslate it. This skill is specifically fine-tuned to transcribe Hinglish directly into Romanized text (e.g., "aap kaise ho"), matching how users naturally type in chat and messaging apps.

    The skill is built on the faster-whisper framework and CTranslate2, allowing it to run efficiently on both CPU and GPU. It is designed to integrate into Python-based AI agent workflows and requires Python 3.9 or higher.

    Yes, the skill runs entirely on your local hardware after the initial model download. This ensures your audio data remains private and eliminates the per-minute costs associated with cloud-based transcription APIs.

    The purchase includes the complete skill implementation, environment configuration scripts (including specific library pinning to prevent crashes), and a pre-configured pipeline for the Nova Whisper Hinglish model.

    The skill uses a high-performance VAD filter to trim silence without cutting off the ends of words. It also implements non-sequential conditioning to prevent the "hallucination loops" or repetitive text generation common in other STT models.