agentmods.dev

speech-mcp GEMINI.md

speech-mcp GEMINI.md is an instructions file for Gemini CLI from sandraschi/speech-mcp. It costs 532 tokens per session, scanned A, original, MIT.

Project instructions for speech-mcp, a voice application with a Python backend and a React web interface. It includes speech recognition, text-to-speech, wake-word detection, and a searchable knowledge store.

In plain words
What is it for?
Use them when working on audio streaming, speech input or output, wake words, the web interface, the knowledge store, or the project’s local APIs.
Why use it?
They give a coding agent the project’s architecture, local service addresses, and development conventions. This reduces the risk of changing the wrong component or connection.

Instructions file for Gemini CLI

not rated 2 5d ago A scan 532 tokens original MIT
View the source file sandraschi/speech-mcp
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 instructions/sandraschi/speech-mcp/gemini-md
Clone the repo
git clone --depth 1 https://github.com/sandraschi/speech-mcp

Made for: Gemini CLI.

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 speech-mcp GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sandraschi/speech-mcp/gemini-md.svg)](https://agentmods.dev/instructions/sandraschi/speech-mcp/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/sandraschi/speech-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/speech-mcp/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 532 This file is loaded in full into every session.
When invoked 532 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00532 $0.00532
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 5d ago against content hash 20dc5d66745c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speech-mcp GEMINI.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 5d 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.

GEMINI.md · 42 lines

What it actually says

Speech-MCP: System Context

This document provides grounding for the AI agent. Refer to this before performing architectural changes, debugging, or tool development.

🛠 Tech Stack

  • Backend: Python 3.12 + FastMCP + FastAPI
  • Frontend: React + Vite + Tailwind v4 + Biome (Linting)
  • Data Layer:
    • RAG: LanceDB + FastEmbed (bge-small-en-v1.5)
    • Storage: JSON-based state in data/
  • Voice Stack:
    • TTS: Gemini 3.1 Flash (Priority), Hume Octave, ElevenLabs, Windows SAPI5
    • STT: Gemini 3.1 Multimodal Live
    • Wake Word: openWakeWord (Offline ONNX Models)

📡 Registry & Ports

  • Backend API: http://localhost:10909
  • Frontend UI: http://localhost:10908
  • WebSocket Gateway: ws://localhost:10909/ws/stream
  • Telemetry Stream: ws://localhost:10909/ws/logs (JSON Payload)

🏗 Directory Structure

  • /src/speech_mcp: Core Python logic and MCP tool definitions
    • server.py: API and MCP entry point
    • streaming.py: WebSocket audio handlers
    • tools/: Modular tool implementations
      • wake_word.py: openWakeWord engine integration
      • speech.py: TTS / Dialogue synthesis
      • rag.py: LanceDB knowledge base
  • /web: React frontend
  • /docs: Detailed technical and user documentation
  • /scripts/demos: Standalone demo scripts for provider testing

🧠 Development Standards

  1. Neutral Branding: Component labels and logs should use technical descriptors (e.g., "Wake-Word Detection"). Avoid redundant status markers like "Alpha" in functional names.
  2. Zero-Diagnostic Policy: Maintain zero Ruff/Biome warnings. Always run just fix before finishing a task.
  3. Semantic HTML: All interactive elements must have unique, descriptive IDs for automated testing.
  4. Tool Integrity: Preserve existing docstrings and FastMCP decorators.

Reference global patterns in D:\Dev\repos\mcp-central-docs\patterns

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. 5d ago First seen · 42 lines · 532 tokens per session scan A 20dc5d66745c

Subscribe to this mod's changes

speech-mcp GEMINI.md is an instructions file published in the GitHub repository sandraschi/speech-mcp (2 stars, last pushed 5d ago), licensed MIT. It adds 532 tokens to every session, about $0.0027 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.

elevenlabsfastmcpfunasrmcpspeech-to-texttext-to-speech
Related

Other instructions, from other repositories

sayna CLAUDE.md

Instructions for SaynaAI/sayna, covering claude.md, project overview, development commands, feature flags and high-level architecture.

SaynaAI/sayna · 3,015 tokens

cadence-code AGENTS.md

AGENTS.md instructions for michael-L-i/cadence-code, covering agent guide, project overview, plugin layout, important paths and local commands.

michael-L-i/cadence-code · 2,720 tokens

cadence-code CLAUDE.md

Claude Code instructions for michael-L-i/cadence-code, covering claude code guide, project summary, claude-specific flow and working expectations.

michael-L-i/cadence-code · 544 tokens

noisy-coding CLAUDE.md

Claude Code instructions for noisy/noisy-coding, covering noisy-coding — agent notes, local development setup, key docs, releasing and restarting the daemon.

noisy/noisy-coding · 865 tokens

AI_Secretary_System CLAUDE.md

Claude Code instructions for ShaerWare/AI_Secretary_System, covering claude.md, project overview, commands, build & run and docker (recommended).

ShaerWare/AI_Secretary_System · 17,310 tokens

cc-hooks CLAUDE.md

Instructions for husniadil/cc-hooks, covering claude.md, documentation structure, best practices, pep 723 for standalone scripts and /// script.

husniadil/cc-hooks · 8,589 tokens