talkies

talkies is a skill for Claude Code from psyb0t/docker-talkies. It costs 179 tokens per session (14,174 once invoked), scanned B, original, WTFPL.

A self-hosted speech service that turns audio into text and text into spoken audio. It also accepts live audio over a WebSocket connection.

In plain words
What is it for?
Use it for audio transcription, live speech recognition, text-to-speech, and IPA phoneme recognition.
Why use it?
It lets applications handle speech locally through an OpenAI-compatible interface.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Part of the talkies plugin — 1 skill shipped together

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 skills/psyb0t/docker-talkies/talkies
Any agent
npx skills add psyb0t/docker-talkies --skill talkies
Clone the repo
git clone --depth 1 https://github.com/psyb0t/docker-talkies

Made for: Claude Code.

Or install talkies, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for talkies

README.md
[![agentmods](https://agentmods.dev/badge/skills/psyb0t/docker-talkies/talkies.svg)](https://agentmods.dev/skills/psyb0t/docker-talkies/talkies)
Your own site
<a href="https://agentmods.dev/skills/psyb0t/docker-talkies/talkies"><img src="https://agentmods.dev/badge/skills/psyb0t/docker-talkies/talkies.svg" alt="Measured on agentmods" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 14,174 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00179 $0.14174
Opus 5 $0.00089 $0.07087
Sonnet 5 $0.00036 $0.02835
Haiku 4.5 $0.00018 $0.01417

Measured 6d ago against content hash 3c8d04acc3d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

talkies scanned grade B with 2 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/bulk_transcribe.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

curl -X PUT --data-binary @lecture.mp3 \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

shell: "Documented setup and workflow examples invoke local curl, ffmpeg, and docker commands."
.agents/skills/talkies/SKILL.md · 741 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

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 741 lines · 179 tokens per session scan B 3c8d04acc3d3

Subscribe to this mod's changes

talkies is a skill published in the GitHub repository psyb0t/docker-talkies (5 stars, last pushed 9d ago), licensed WTFPL. It adds 179 tokens to every session and 14,174 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

tianji-data-query

Query website analytics, monitor uptime, survey results, telemetry data, feed events, application stats, and more from the Tianji platform via its read-only OpenAPI (69 GET endpoints across 14 service domains). Use when the user asks about website traffic, pageviews, monitor status, survey feedback, telemetry events…

msgbyte/tianji · 82 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

davila7/claude-code-templates · 67 tokens

video2knowledge

Convert videos into timestamped subtitles and structured knowledge artifacts. Two ingestion paths: (1) a native multimodal VLM (at most 4B params, via Ollama) reads sampled video frames into timestamped captions; (2) faster-whisper ASR transcribes the audio into timestamped subtitles. Then refine into a structured…

CacinieP/video2knowledge · 161 tokens

file-issue

File a GitHub issue on this repo with the required title prefix and labels. Use when opening an issue, or when a finding during other work is worth tracking rather than fixing inline.

piperbox/piper · 41 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

OpenLAIR/dr-claw · 67 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

synthetic-sciences/openscience · 67 tokens