audio-brief skillA
audio-brief is agent-read markdown (skill) from calebnewtonusc/chewbacca: Turn a piece of work into something the user can listen to instead of read. Use when they say they want to hear it, listen to it, put it in their ears, or that they will be driving, walking, at the gym, doing laundry, or otherwise away from the screen. Also use when handing over a long analysis they will not sit and read, and when they ask for a voice memo, an audio summary, or a recording of a briefing..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Audio brief Two jobs, and the second one is the hard one. Rendering text to speech is a command. Writing something worth listening to is the craft, and skipping it produces a file that is technically audio and practically unlistenable. ## Render it ```bash brief-audio script.txt # -> script.mp3 brief-audio -v am_michael notes.txt # different voice echo "some text" | brief-audio -o out.mp3 ``` Kokoro-82M, Apache 2.0, local, no API key and no network after the first run caches the model. First run installs espeak-ng, ffmpeg and a Python 3.12 venv at `~/.chewbacca/audio-venv`, which takes about a minute. Every run after is faster than real time. Voices: `af_heart` (default, highest quality grade), `af_bella`, `af_nicole`, `af_sarah`, `am_michael`, `am_puck`, `am_adam`, `bf_emma`, `bm_george`. **Do not reach for a paid TTS API.** That was the first instinct on 2026-09-20 and it was wrong: it needed a key Caleb did not have, so the work stalled on a credential for something a local Apache-2.0 model does well. If a hosted voice is ever specifically wanted, that is a deliberate choice, not the default. ## Write it for the ear first …
Read the whole file at its exact version.
How to install
mdr add calebnewtonusc/chewbacca/audio-brief@git:20260923.c7250b6mdr add calebnewtonusc/chewbacca/audio-brief@sha256:e21656f1cd1264dePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ftwzzlqvvk4twvyw)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.c7250b6 latest | 2026-09-23 | c7250b6 | 4,908 B | A | view · diff |
| git:20260921.80fa5b2 | 2026-09-21 | 80fa5b2 | 4,910 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4908 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
calebnewtonusc/chewbacca · 8 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ftwzzlqvvk4twvyw GET https://markdownregistry.com/api/v1/resolve?ref=calebnewtonusc/chewbacca/audio-brief GET https://markdownregistry.com/api/v1/blob/e21656f1cd1264ded4bf37a2e1be280ecc121a01ccb9dc86b588aaf70b293f3e
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.