Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    pdf to audiobook-mp3

    1

    Convert searchable PDFs into MP3 audiobooks using Edge-TTS, ElevenLabs, or local SAPI voices.

    Free

    Security scanned
    pdf to audiobook-mp3

    pdf to audiobook-mp3

    Example session with this skill installed

    Convert the attached "q3_report.pdf" to an MP3 using the default Edge voice. Put it on my desktop.

    • Read your context and instructions
    • Compiled the pdf to audiobook-mp3

    I have processed the document and converted it to speech using the Edge-TTS engine with the en-US-GuyNeural voice. A dry-run preview was performed first to ensure the text extraction correctly captured the report headers and data tables.

    Conversion Results

    File NameVoiceDurationStatusPath
    q3_report.mp3en-US-GuyNeural12:45SuccessC:\Users\Dev\Desktop\q3_report.mp3

    Conversion Details

    • Engine: Microsoft Edge-TTS (Online)
    • Language: en-US
    • Chunks Processed: 14
    • Audio Validation: Passed (192kbps)

    Next steps

    • I can regenerate this using a female voice (e.g., en-US-EmmaNeural) if you prefer.
    • If you have more documents, I can batch-process them into the same folder.
    • Type "open menu" if you would like to adjust the speech rate or pitch via the GUI.

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

    About this skill

    Reading dense PDFs is time-consuming and often impossible while commuting or multitasking. This skill converts searchable PDFs into high-quality MP3 audiobooks using professional speech engines.

    What it does

    • Multi-Engine Support converts text using Microsoft Edge-TTS (online), ElevenLabs (high-fidelity), or Windows SAPI (offline).
    • Desktop Interface launches a bundled GUI for users who prefer point-and-click control over voices, quality settings, and file selection.
    • Smart Text Cleaning removes meeting timestamps, invisible PDF markers, and layout-driven artifacts to ensure natural prosody.
    • Batch Processing handles multiple documents in sequence, producing one validated MP3 per input file with automatic numeric suffixing.
    • Contextual Synthesis maintains consistent voice tone across ElevenLabs request boundaries by analyzing neighboring text and punctuation.

    How it works

    1. Pre-flight Check verifies Python 3.10+ dependencies and runs a dry-run preview to inspect text extraction and reading order.
    2. Configuration selects the voice engine and locale based on document language or user preference (e.g., en-US-GuyNeural).
    3. Synthesis processes text in optimized chunks, coalescing paragraph breaks and stitching audio fragments to preserve cadence.
    4. Validation confirms the output MP3 is non-empty, validates audio integrity, and reports final duration to the user.

    Frameworks & tools

    Built with Python. It utilizes Edge-TTS for free online narration, the ElevenLabs API for premium voices, and Windows SAPI for local processing. Requires pdfminer.six for extraction.

    Why this beats prompting it yourself

    Standard LLM prompting cannot handle the binary extraction, audio stitching, or multi-minute synthesis required for full books. This skill manages the entire pipeline, including layout-aware text cleaning and API credit-saving dry runs, which a raw prompt would skip.

    Use cases

    • Convert technical whitepapers into audio for listening during commutes.
    • Generate high-fidelity narration for long-form documents using ElevenLabs.
    • Batch-process a folder of PDF reports into a narrated audio playlist.
    • Provide an offline text-to-speech solution using local Windows voices.

    Known limitations

    Does not perform OCR; requires searchable text PDFs. GUI mode requires a graphical desktop environment and is unavailable on headless hosts. Kokoro and Piper engines require separate manual installation.

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

    Requires searchable PDFs (no OCR). GUI requires a non-headless OS. ElevenLabs requires a paid API key. Rate/pitch adjustments are limited to Edge-TTS engine.

    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

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Software
    PythonGit

    Permissions

    Terminal / Shell
    Write Files
    Read Files
    Network Access
    Environment Variables
    Listed27 days ago
    Updated11 days ago

    What's inside

    Frequently Asked Questions

    No, this skill requires PDFs to have a text layer. It cannot currently extract text from images or scanned documents that have not been processed with Optical Character Recognition (OCR).

    You can choose between Microsoft Edge-TTS (free, online), Windows SAPI (free, offline), or the ElevenLabs API (requires your own API key for high-fidelity voices). This flexibility allows you to balance cost and audio quality.

    The skill includes a 'Smart Text Cleaning' feature that automatically detects and removes common PDF artifacts like layout markers and timestamps, ensuring the narrator doesn't read aloud distracting metadata.

    The package includes the core Python automation scripts, a user-friendly desktop GUI, and comprehensive documentation for configuration. Buyers receive lifetime access to the current version and any future patches or voice engine updates.

    Yes, the skill features a Batch Processing mode that allows you to point to a folder and convert multiple documents sequentially into a narrated MP3 playlist with automatic file naming.

    The skill is compatible with any environment running Python 3.10+, including Windows, macOS, and Linux. However, the local SAPI voice engine and the graphical GUI are specific to Windows desktop environments.

    New in Workflow Automation

    Free