Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    koe voiceover

    1

    Convert text to speech for videos and demos using a free MCP-based TTS studio with neural voices.

    Free

    Security scanned
    koe voiceover

    koe voiceover

    Example session with this skill installed

    Generate a voiceover for this intro script using a professional male voice: 'Welcome to the system demo. Today we will explore the API architecture.' Save it as intro-scene.

    • Read your context and instructions
    • Compiled the koe voiceover

    I have generated the voiceover for your intro script using the en-US-GuyNeural voice on the edge engine. The audio is ready for download.

    Voiceover Generation Details

    PropertyValue
    Job IDjob_af82k91z0
    File Nameintro-scene.mp3
    Voiceen-US-GuyNeural (Edge Engine)
    Word Count14 words
    Character Count88 characters
    Statuscompleted
    Download URLhttps://koe.kennedyazeru.space/download/job_af82k91z0?sig=5e8f2...
    Expires In14 minutes

    Next steps

    • Download the MP3 file immediately using the signed URL above.
    • If you need a faster pace for the video, I can regenerate this with rate: 1.15.
    • Provide the script for the next scene to continue the narration sequence.

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

    About this skill

    Writing video scripts or long-form content is useless if you cannot turn them into audio without expensive subscriptions. Koe-voiceover bridges the gap between text generation and production-ready audio by providing a direct interface to a free text-to-speech studio via MCP.

    What it does

    • Synthesize speech from prose using Microsoft neural voices or offline Piper engines.
    • Manage narration across multiple scenes with consistent voice, rate, and pitch settings.
    • Handle quotas automatically by tracking word counts and request limits across hourly and daily windows.
    • Recover from failures by checking engine status, queue depth, and circuit breakers before retrying.
    • Retrieve audio via signed download URLs or direct local file paths for integration into video pipelines.

    How it works

    1. Use studio_status to verify engine availability and check current queue depth.
    2. Call list_voices to select a voice ID compatible with your chosen engine (e.g., edge, piper, or kokoro).
    3. Execute generate_voiceover with your script, adjusting the rate for a natural reading speed.
    4. Download the generated MP3 or WAV file using the provided short-lived URL or local path.

    Frameworks & tools

    This skill interfaces with the Koe TTS Studio MCP server. It is designed for workflows involving Remotion, HyperFrames, ffmpeg, and other automated video or podcast production pipelines.

    Why this beats prompting it yourself

    Prompting an agent to "make audio" usually results in a link to an external site or a generic API error. This skill provides the specific logic needed to mint free keys, manage stateless job IDs, and handle complex rate limits that typical LLMs cannot track on their own.

    Use cases

    • Generating per-scene narration files for automated video explainers.
    • Creating audio versions of technical READMEs or blog posts.
    • Scaffolding placeholder voice tracks for product demos.
    • Building a spoken newsletter archive from existing text content.

    Known limitations

    Keys are limited to 3 per IP per day with a 2,000 word per hour quota. The hosted endpoint requires downloading files within 15 minutes before they are deleted from the server.

    Free keys capped at 3 per IP daily. 2,000 words/hour quota. Hosted audio files expire after 15 minutes. No support for music or voice cloning.

    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 2 days ago

    • Free with an Agensi account

    Requires

    Kennedyazeru

    Permissions

    Write Files
    Network Access

    Allowed Hosts

    koe.kennedyazeru.space
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    This skill provides a direct interface to high-quality neural voices through the MCP (Model Context Protocol), allowing you to automate audio production without manually navigating external websites or managing complex API rate limits.

    The skill supports various engines including Microsoft Edge neural voices for cloud-based quality, as well as Piper and Kokoro for offline or localized processing.

    Yes, the skill is designed to manage per-scene narration, allowing you to define consistent voice settings (rate, pitch, and style) across multiple individual audio files for a single project.

    While the service is free to use, there is an automated quota of 2,000 words per hour and a limit of 3 keys per IP per day to ensure stability for all users.

    Generated audio files are available via short-lived URLs or local paths; if using the hosted endpoint, you must download or move your files within 15 minutes before they are automatically purged.

    This skill is compatible with any AI agent or platform that supports the Model Context Protocol (MCP), making it ideal for integration with automation tools like Remotion or ffmpeg.

    New in Agents & Orchestration