What is Speak-Turbo AGENTS.md?

Project instructions for Speak-Turbo, a text-to-speech system that turns written text into spoken audio. They describe its Python background service, Rust command-line client, local HTTP endpoints, cached voices, and idle shutdown.

Use it when developing or debugging the Speak-Turbo daemon, Rust client, local health and speech endpoints, audio streaming, voice caching, or automatic shutdown.

Contributors need to know which component owns the service, how the client communicates with it, and where the model and voice state are kept. The instructions reduce confusion when changing this two-part system.

How EmZod/Speak-Turbo configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to EmZod/Speak-Turbo. 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/EmZod/Speak-Turbo/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/EmZod/Speak-Turbo

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/emzod/speak-turbo/agents-md.svg)](https://agentmods.dev/instructions/emzod/speak-turbo/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/emzod/speak-turbo/agents-md"><img src="https://agentmods.dev/badge/instructions/emzod/speak-turbo/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 768 This file is loaded in full into every session.

When invoked 768 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.

Model	Per session	Once invoked
Fable 5.1	$0.00768	$0.00768
Opus 5	$0.00384	$0.00384
Sonnet 5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 7d ago against content hash 03c4aadbf655, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Speak-Turbo AGENTS.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 7d 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.

AGENTS.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents working on the Speak-Turbo codebase.

Using speakturbo? See SKILL.md instead.

Project Structure

speakturbo/              # Python daemon
├── daemon_streaming.py  # Main FastAPI server (port 7125)
├── cli.py               # Python CLI fallback
└── tests/               # pytest tests

speakturbo-cli/          # Rust CLI (primary interface)
├── Cargo.toml
└── src/main.rs          # Streaming HTTP client + audio playback

Architecture

User → speakturbo (Rust) → HTTP GET /tts → daemon_streaming.py → pocket-tts → audio stream
                                              ↓
                                         Model in memory (TTSModel)
                                         Voice states cached
                                         Auto-shutdown after 1hr idle

The Rust CLI exists purely for latency — it starts in ~1ms vs Python's ~100ms interpreter startup.

Single Daemon Design

There is exactly one daemon implementation: daemon_streaming.py.

Port: 7125 (hardcoded)
API: GET /health, GET /tts?text=...&voice=...
Host: 127.0.0.1 (localhost only, with DNS rebinding protection)
Auto-shutdown: 1 hour idle timeout

Development

# Python daemon
pip install -e .
python -m speakturbo.daemon_streaming

# Rust CLI
cd speakturbo-cli
cargo build --release
./target/release/speakturbo "test"

# Tests
pytest speakturbo/tests/ -v

Key Files

File	Purpose
`daemon_streaming.py`	FastAPI app, `/health` and `/tts` endpoints
`speakturbo-cli/src/main.rs`	HTTP streaming, audio buffer, rodio playback
`cli.py`	Python CLI fallback (when Rust not available)
`SKILL.md`	User-facing documentation

Design Decisions

Daemon architecture: Model loading is slow (~3s). Keep it resident.
Rust CLI: Python startup adds 100ms. Rust adds ~1ms.
HTTP streaming: Start playback before generation completes.
Auto-shutdown: Free memory after 1hr idle. Users don't manage daemons.
No voice cloning: Simplicity. Use speak (Chatterbox) for that.
Localhost-only: Daemon binds to 127.0.0.1 with DNS rebinding protection.
Output path allowlist: -o flag restricted to /tmp, $PWD, ~/.speakturbo/ by default. --allow-dir for one-off overrides, ~/.speakturbo/config for permanent additions.

Read the full file on GitHub · 90 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.

7d ago First seen · 90 lines · 768 tokens per session scan A 03c4aadbf655

Subscribe to this mod's changes

Speak-Turbo AGENTS.md is an instructions file published in the GitHub repository EmZod/Speak-Turbo (20 stars, last pushed 6mo ago), licensed MIT. It adds 768 tokens to every session, about $0.0038 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 2026-08-30.

ai-agents local-first streaming text-to-speech

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 · 5,182 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

Speak-Turbo: Instructions file for Codex