Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Tts Voice Announcer

    1

    Turn any text into spoken audio with edge-tts: pick from 100+ neural voices, tune rate, pitch, and volume, convert to mp3, and play it back locally. Use when a

    Free

    4 usesSecurity scanned
    Tts Voice Announcer

    Tts Voice Announcer

    Example session with this skill installed

    Read the content of script.txt using a British male voice. Make it sound slightly slower and deeper, then play it back.

    • Read your context and instructions
    • Compiled the tts voice announcer

    Synthesized script.txt using en-GB-RyanNeural at -10% rate and -5Hz pitch. MP3 saved and played. MEDIA:/tmp/narration.mp3. Spoken text: "System migration initiated. Please standby for updates."

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

    About this skill

    The problem

    Generating high-quality speech usually requires expensive cloud API subscriptions or complex local model hosting. Developers need a way to add vocal announcements, accessibility read-outs, or narration to their tools without managing API keys or heavy infrastructure.

    What it does

    • Converts text or local files into MP3 audio using neural voices.
    • Provides access to over 100 high-quality Microsoft Edge neural voices across multiple locales.
    • Adjusts speaking rate, pitch, and volume via simple percentage offsets.
    • Handles local audio playback on macOS and Linux systems for immediate feedback.
    • Automates voice selection and synthesis for system alerts or script narration.

    Frameworks & tools

    Uses edge-tts via Python, afplay (macOS), and aplay or ffplay (Linux).

    Why this beats prompting it yourself

    Standard LLM prompts often hallucinate TTS commands or fail to handle shell quoting for long scripts. This skill provides a structured workflow for voice discovery, parameter tuning, and reliable file delivery with proper media attachment handling.

    Use cases

    • Announce build completions or deployment statuses in the terminal.
    • Generate scratch-track narration for video or podcast drafts.
    • Create audio versions of long-form articles for accessibility.
    • Build interactive voice responses for local automation scripts.

    Known limitations

    Requires local installation of edge-tts via pip. Not recommended for commercial redistribution or complex SSML requirements.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Requires edge-tts and local audio players like afplay or ffplay. Not for commercial audio redistribution or complex SSML needs.

    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 buying a skill.

    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

    4 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill enables your AI agent to generate high-quality neural speech from text or local files, providing over 100 voices with adjustable pitch and speed without requiring expensive cloud API subscriptions.

    The skill is designed for local environments on macOS and Linux, utilizing system-native players like afplay and ffplay for immediate audio feedback.

    No cloud API keys are required; however, you will need to have Python and the `edge-tts` package installed locally on your machine for the synthesis to function.

    Your purchase includes the full skill workflow, including pre-configured logic for voice discovery, parameter tuning (rate/pitch/volume), and reliable MP3 file handling.

    Yes, the skill allows you to pass specific percentage offsets for speaking rate, pitch, and volume, giving you fine-grained control over how the neural voice sounds.

    While the skill provides access to over 100 high-quality Microsoft Edge neural voices, it is not designed for complex SSML (Speech Synthesis Markup Language) or commercial redistribution of the audio files.

    Free