agentmods.dev

talky-talky: Instructions file for Claude Code

CLAUDE.md

talky-talky CLAUDE.md is an instructions file for Claude Code from shawnrushefsky/talky-talky. It costs 1,446 tokens per session, scanned A, original, MIT.

Project instructions for Talky Talky, an MCP server that gives AI agents speech, transcription, song-generation, and audio-analysis tools.

In plain words
What is it for?
Use them when developing or maintaining Talky Talky, including its text-to-speech, speech-to-text, audio-processing, voice-analysis, and asset-management features.
Why use it?
They give the agent the project overview, architecture, technology stack, engine references, installation guidance, and tool documentation it needs to work consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is shawnrushefsky/talky-talky's own configuration. It tells Claude Code how to work on talky-talky itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything talky-talky configures →

not rated 2repo 8mo ago A scan 1,446 tokens original MIT
View source ↗ shawnrushefsky/talky-talky
Reuse

Borrowing it

Nothing to install: this file belongs to shawnrushefsky/talky-talky. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/shawnrushefsky/talky-talky/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/shawnrushefsky/talky-talky

Made for: Claude Code.

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 talky-talky CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/shawnrushefsky/talky-talky/claude-md/github.svg)](https://agentmods.dev/instructions/shawnrushefsky/talky-talky/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/shawnrushefsky/talky-talky/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnrushefsky/talky-talky/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for talky-talky CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/shawnrushefsky/talky-talky/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnrushefsky/talky-talky/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,446 This file is loaded in full into every session.
When invoked 1,446 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.01446 $0.01446
Opus 5 $0.00723 $0.00723
Sonnet 5 $0.00289 $0.00289
Haiku 4.5 $0.00145 $0.00145

Measured 10d ago against content hash 62f9714d66de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

talky-talky CLAUDE.md 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 10d ago.

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.

CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Talky Talky - Development Guide

MCP server providing Text-to-Speech, Speech-to-Text, and audio processing for AI agents.

Quick Reference

Documentation Contents
docs/engines/tts.md TTS engine reference (Maya1, Chatterbox, XTTS, etc.)
docs/engines/songgen.md Song generation (LeVo/SongGeneration)
docs/engines/transcription.md Whisper, Faster-Whisper reference
docs/engines/analysis.md Emotion, voice similarity, quality analysis
docs/adding-engines.md How to add new TTS engines
docs/tools-reference.md Complete MCP tools list
docs/audio-features.md Voice modulation, asset management
docs/installation.md Installation and MCP client setup

Project Overview

Engines:

  • TTS: Maya1 (voice design), Chatterbox/Turbo (voice cloning), MiraTTS, XTTS-v2, Kokoro, Soprano, VibeVoice, CosyVoice3, SeamlessM4T
  • Song Generation: LeVo (complete songs from lyrics, CUDA-only)
  • Transcription: Whisper, Faster-Whisper (4x faster)
  • Analysis: Emotion2vec (emotion), Resemblyzer (voice similarity), NISQA (quality)
  • Assets: Local indexing, Freesound.org, Jamendo (music)

Audio utilities: format conversion, concatenation, normalization, trimming, crossfade, mixing, effects, voice modulation (pitch/time/formant shifting)

Architecture

Technology Stack

  • Runtime: Python 3.11+ (required for TTS library compatibility)
  • MCP SDK: mcp with FastMCP
  • Audio Processing: ffmpeg
  • Package Manager: uv

Directory Structure

talky_talky/
├── server/               # MCP server package
│   ├── app.py            # Server entry point with MCP tools
│   └── config.py         # Configuration utilities
├── tools/
│   ├── audio/            # Audio utilities package
│   │   ├── types.py      # Dataclasses (AudioInfo, results, etc.)
│   │   ├── utilities.py  # Core functions (convert, concatenate, normalize)
│   │   ├── trimming.py   # Trim, silence detection, crossfade
│   │   ├── design.py     # Mix, volume, fade, effects, overlay
│   │   └── modulation.py # Pitch shift, time stretch, voice effects, formant
│   ├── tts/              # TTS engines (base.py, utils.py, maya1.py, ...)
│   ├── songgen/          # Song generation (base.py, levo.py, acestep.py)
│   ├── transcription/    # STT engines (whisper.py, faster_whisper.py)
│   ├── analysis/         # Analysis engines (emotion2vec.py, resemblyzer.py, nisqa.py, sfx.py)
│   ├── assets/           # Asset management (database.py, local.py, freesound.py)
│   ├── autotune.py       # Vocal autotune
│   ├── pitch_detection.py # Pitch detection utilities
│   └── music_theory.py   # Scales and keys constants
└── utils/
    └── ffmpeg/           # ffmpeg wrapper package
        ├── core.py       # Base utilities (check_available, get_audio_info)
        ├── format.py     # Format conversion, normalization
        ├── concat.py     # Concatenation, crossfade join
        └── manipulation.py # Trim, silence, effects

Read the full file on GitHub · 146 lines

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. 10d ago First seen · 146 lines · 1,446 tokens per session scan A 62f9714d66de

Subscribe to this mod's changes

talky-talky CLAUDE.md is an instructions file published in the GitHub repository shawnrushefsky/talky-talky (2 stars, last pushed 8mo ago), licensed MIT. It adds 1,446 tokens to every session, about $0.0072 per session on Opus 5. 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.

Creative and mediamcpstttext-to-audiotext-to-speechtranscriptiontts
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens