- Home
- Skills
- Workflow Automation
- audio tldr
audio tldr
Transcribe and summarize audio or video from URLs and local files into structured digests with local caching.
Free
Works with the AI Agents you already use
audio tldr
Example session with this skill installed
- Read your context and instructions
- Compiled the audio tldr
Rust in 100 Seconds (Fireship, ~2:27)
Key takeaways
- Rust is a memory-safe, compiled language built for performance-critical systems (game engines, databases, OSes) and is also a strong fit for WebAssembly.
- Created by Graydon Hoare in 2007 as a side project, gained Mozilla sponsorship in 2009, and has topped "most loved language" surveys every year since 2016.
- Unlike garbage-collected languages or manual-memory languages (malloc/free), Rust achieves memory safety through
ownership and borrowing, with no garbage collector at runtime.
- Variables are immutable by default, letting simple values live cheaply on the stack; mutable values or those with unknown compile-time size go on the heap.
- Every value has exactly one owner variable; when that variable goes out of scope, its memory is freed automatically. Borrowing (via
&) lets other code reference a value without taking ownership. - The borrow checker enforces these rules at compile time, catching memory bugs before the program runs — trading compile-time friction for runtime safety and speed.
- Practically: Cargo is Rust's package manager (packages = "crates");
cargo newscaffolds a project,main.rsholds the entry-pointmainfunction, and the standard library covers I/O, filesystem, and concurrency.
Summary
This is Fireship's rapid-fire intro to Rust, framing it as a memory-safe systems language that sidesteps the classic tradeoff between garbage-collected languages (safe but less control) and low-level languages like C (fast but easy to shoot yourself in the foot). Rust's answer is ownership and borrowing: each value has one owner, memory frees automatically when that owner goes out of scope, and a compile-time borrow checker enforces reference rules so memory bugs surface before the code ever runs. The video covers Rust's history and ecosystem (Cargo, crates, standard library), then walks through the basics of setting up and compiling a simple program using let, mut, and println!.
Saved at ./audio-tldr-output/rust-in-100-seconds-20260803-key-takeaways.md.
Real output: the run shown in the demo at the top of the project README, summarized from a cached transcript.
Connects securely to your tools. The creator never sees your data.
About this skill
Transcribing and summarizing audio/video content is a resource-intensive chore that often requires juggling Python scripts, FFmpeg, and LLM APIs. This skill automates the entire pipeline, turning URLs or local files into structured takeaways while maintaining a local cache to avoid redundant transcription costs.
What it does
- Automated Transcription uses Whisper backends to convert video and audio files into text locally.
- Intelligent Summarization distills long transcripts into meeting minutes, analysis reports, or key takeaways.
- Smart Name Correction cross-references transcriptions against media metadata and user glossaries to fix misheard names.
- Visual Extraction captures slides or frames from video sources to illustrate the digest.
- Translation provides full-transcript or summary translations into target languages.
- Privacy-first: audio is transcribed locally and never uploaded; an optional mode keeps the digest on your own Ollama server too.
How it works
- Transcribe. Provide a YouTube URL, Apple Podcast link, or local file. The skill runs a cached transcription phase using the best available local Whisper backend.
- Configure. Select a template like
meeting-minutesorkey-summary, or describe a custom focus for the digest. - Digest. The skill processes the transcript through a subagent or local Ollama, applying name-correction rules and visual frames if requested.
- Export. The final digest is saved to a designated output folder in Markdown or HTML format.
Frameworks & tools
Built with Python, utilizing yt-dlp for media fetching and ffmpeg for processing. It supports various Whisper backends including mlx-whisper, faster-whisper, and whisper.cpp. Integrates with Ollama for local LLM workflows.
Why this beats prompting it yourself
Manual prompting requires you to handle file downloads, manage context window limits for long transcripts, and manually fix common speech-to-text errors. This skill manages the local cache, automates chunking for long content, and applies a conservative name-correction rule that fixes misheard names from the source's own details and lists every correction it makes.
Use cases
- Generate structured meeting minutes from Zoom or Google Meet recordings.
- Convert hour-long technical podcasts into five-minute skimmed summaries.
- Extract visual slides and key points from recorded webinars or tutorials.
- Create localized translations of foreign language interviews with timestamped references.
Known limitations
Requires local installation of FFmpeg, yt-dlp, and at least one Whisper backend. Transcription speed depends heavily on local hardware. Subtitles for a source already transcribed as plain text need one re-transcription.
Requires local FFmpeg, yt-dlp, and a Whisper backend. Transcription speed depends on hardware. Frames cannot be extracted from pure audio. Subtitles require re-transcribing if not requested initially.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 month ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
File Scopes
Runs local Python scripts (yt-dlp, ffmpeg, Whisper) through the shell. Network is used to download the media you give it (via yt-dlp) and, for Apple Podcasts links, the public iTunes lookup and the show's RSS feed. Audio is transcribed locally and never uploaded; the transcript text is read by your agent's model to write the digest (or by your own Ollama server in the optional local mode). Transcripts are cached in ~/.cache/audio-tldr, digests are saved to ./audio-tldr-output, and optional preferences, templates and a glossary are read from ~/.config/audio-tldr. Local media files you point it at are read, never modified.