More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    voice dispatcher skill

    1

    High-latency sequential TTS calls stall production pipelines.

    Free

    Security scanned
    voice dispatcher skill

    voice dispatcher skill

    Example session with this skill installed

    Synthesize these three phrases using voice ID 'pNInz6obpgDQGcFmaJgB': 'System online.', 'Battery at twenty percent.', 'Recharging now.'

    • Read your context and instructions
    • Compiled the voice dispatcher

    I have processed the batch text-to-speech request. The phrases were synthesized in parallel using the ElevenLabs API and the resulting audio files have been uploaded to your Supabase bucket.

    Synthesis Results

    PhraseStatusPublic Audio URL
    System online.Successhttps://xytz.supabase.co/storage/v1/object/public/audio/4a1b2c.mp3
    Battery at twenty percent.Successhttps://xytz.supabase.co/storage/v1/object/public/audio/9d8e7f.mp3
    Recharging now.Successhttps://xytz.supabase.co/storage/v1/object/public/audio/3g2h1j.mp3

    Metadata

    • Total Processed: 3 phrases
    • Execution Time: 2.15 seconds
    • Voice ID: pNInz6obpgDQGcFmaJgB
    • Delivery Mode: cloud_url

    Next steps

    • Verify the audio quality at the provided CDN links.
    • Integrate the URLs into your application's notification state or database.
    • Adjust stability and similarity_boost in the payload for future batches if the tone needs refinement.

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

    About this skill

    High-latency sequential TTS calls stall production pipelines. This skill provides an asynchronous microservice for batch text-to-speech synthesis using ElevenLabs, featuring parallel execution and instant cloud persistence.

    What it does

    • Parallel Synthesis processes multiple text phrases simultaneously to reduce total execution time.
    • Concurrency Control implements a strict semaphore to manage API rate limits and prevent request failures.
    • Cloud Persistence uploads audio artifacts to Supabase Storage immediately after generation.
    • CDN Generation returns public URLs for each audio file for instant web delivery.
    • Batch Processing handles up to 5 phrases per request with centralized voice settings.

    How it works

    1. Prepare Payload by generating a payload.json file containing the text strings and optional voice settings.
    2. Execute Dispatcher by running the Python script with the input file argument.
    3. Capture Output by reading the structured JSON returned to stdout, which includes the CDN links.

    Frameworks & tools

    Python, ElevenLabs API for high-fidelity synthesis, and Supabase Storage for audio hosting and distribution.

    Why this beats prompting it yourself

    Writing boilerplate for async Python, handling rate-limited semaphores, and managing multi-step storage uploads is error-prone. This skill encapsulates the entire pipeline from raw text to public URL in a single CLI call.

    Use cases

    • Generating multiple dialogue lines for game characters in one pass.
    • Creating audio versions of social media posts or headlines for batch publishing.
    • Producing dynamic voice notifications for web or mobile applications.

    Known limitations

    Limited to 5 phrases per batch. Requires local Python environment and pre-configured ElevenLabs and Supabase API keys in a .env file.

    Strict batch limit of 5 phrases per execution. Requires pre-configured ElevenLabs and Supabase credentials in the environment.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    • Free with an Agensi account

    Requires

    ElevenLabs
    Supabase
    Python
    uv (Python tool runner)
    Git
    ElevenLabs API Key
    Supabase Project URL
    Supabase Secret Key
    Supabase Bucket Name
    uv (Python tool runner)

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    api.elevenlabs.io
    supabase.com
    Listed7 days ago

    What's inside

    Frequently Asked Questions

    The skill solves the bottleneck of high-latency sequential API calls by using asynchronous parallel processing, reducing the time it takes to generate multiple audio files from minutes to seconds.

    The purchase includes the core Python synthesis engine, a pre-configured Supabase storage integration module, and a README documentation file for quick environment setup.

    Yes, you will need active API keys for both ElevenLabs and Supabase (with a storage bucket created) to be stored in your local .env file for the skill to function.

    While designed as a standalone Python CLI tool, it can be easily integrated into any AI agent framework or automation pipeline that supports executing shell commands and parsing JSON outputs.

    The skill includes a built-in semaphore-based concurrency controller that automatically manages the flow of requests to prevent hitting ElevenLabs rate limits or triggering 429 errors.

    By default, the skill supports up to 5 phrases per batch to ensure stability and speed, though this can be adjusted within the source code to suit your specific API tier limits.

    New in APIs & Backend