agentmods.dev

talkies

A self-hosted, OpenAI-compatible speech service that turns speech into text and text into speech over HTTP, with live speech recognition over WebSocket.

In plain words
What is it for?
Use it for audio transcription, live speech recognition, and spoken-audio generation; it also supports speech recognition and file staging through MCP.
Why use it?
It provides a speech interface that can run on your own infrastructure and work with clients expecting OpenAI-compatible APIs.

Plugin for Claude CodeCodex

5 4d ago A scan tokens not measured WTFPL
View the source file psyb0t/docker-talkies
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add plugins/psyb0t/docker-talkies/agents
Claude Code
/plugin marketplace add psyb0t/docker-talkies
Clone the repo
git clone --depth 1 https://github.com/psyb0t/docker-talkies

Made for: Claude Code, Codex.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

talkies scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/.claude-plugin/plugin.json · 23 lines

The source is not reproduced here

Licensed WTFPL

The repository is licensed WTFPL, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 23 lines scan A 13d77dce882b

Subscribe to this mod's changes

talkies is a plugin published in the GitHub repository psyb0t/docker-talkies (5 stars, last pushed 4d ago), licensed WTFPL. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIsCreative and mediaDevOps and cloudOpenAI APIasrdockermcpself-hostedspeech-recognition
Related

Other plugins, from other repositories

hal-voice

Play HAL 9000 voice clips on Claude Code hook events.

vinta/hal-9000 · not measured

xonovex-skill-audio

Xonovex Low-level audio skills.

xonovex/platform · not measured

yt-transcript

Get a plain-text transcript for any video URL: YouTube captions when they exist, fast local Parakeet TDT transcription when they don't.

ykdojo/yt-transcript · not measured

ledgr

Connect AI assistants to your Ledgr personal finance data.

KenTaniguchi-R/ledgr · not measured

audiolla

Self-hosted audio-production API — stem separation, mastering, MIR analysis, DSP chains, MIDI, and AI restoration over REST and MCP.

psyb0t/docker-audiolla · not measured

portal-tunnel

Portal agent workflows for exposing local apps.

gosuda/portal-tunnel · not measured