A text-to-speech tool that turns written text into a spoken audio file.

It is for making narration, voiceovers, pronunciation clips, accessibility readings, and other requested voice recordings.

It provides an audio version of text when reading it is inconvenient or when spoken delivery is needed.

speech — Skill for Claude Code and Codex by tallesborges: A text-to-speech tool that turns written text into a…

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/tallesborges/zdx/speech

Any agent

npx skills add tallesborges/zdx --skill speech

Clone the repo

git clone --depth 1 https://github.com/tallesborges/zdx

Made for: Claude Code, Codex.

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/skills/tallesborges/zdx/speech.svg)](https://agentmods.dev/skills/tallesborges/zdx/speech)

Your own site

<a href="https://agentmods.dev/skills/tallesborges/zdx/speech"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/speech.svg" alt="Measured on agentmods" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,207 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5	$0.00086	$0.01207
Opus 5	$0.00043	$0.00603
Sonnet 5	$0.00017	$0.00241
Haiku 4.5	$0.00009	$0.00121

Measured 5d ago against content hash f15fe376d646, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speech 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.

crates/zdx-assets/bundled_skills/speech/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speech – Text-to-Speech via `zdx speak`

Turn text into a spoken audio file using ZDX's native zdx speak command. In the Telegram bot, the audio is delivered as a real voice note (waveform + playback speed).

Only use this skill when the user explicitly asks for audio/voice output. For normal replies, answer with text.

CLI reference

zdx speak <TEXT> [OPTIONS]

Options:
  -o, --out <PATH>        Output audio path (default: $ZDX_HOME/artifacts/speech/speech-<timestamp>.ogg)
      --provider <NAME>   mistral (default), openai, gemini, or xai
      --model <MODEL>     Provider-prefixed override, e.g. openai:gpt-4o-mini-tts, mistral:voxtral-mini-tts-latest, gemini:gemini-3.1-flash-tts-preview
      --voice <VOICE>     Provider-specific voice (see below)
      --format <FORMAT>   ogg (default, voice note) | mp3 | opus | aac | flac | wav | pcm

Output: prints the saved file path to stdout.

Delivering audio (important)

To send the audio to the user in the bot, emit the output path as a <media> tag at the end of your reply:

<media>/absolute/path/to/speech-XXXX.ogg</media>

.ogg/.oga/.opus → sent as a voice note (sendVoice)
.mp3/.m4a/.wav → sent as an audio message (sendAudio)

Prefer the default .ogg so the user gets a proper voice note. When $ZDX_ARTIFACT_DIR is set, write there:

zdx speak "Hello there" --out "$ZDX_ARTIFACT_DIR/greeting.ogg"

Providers & voices

Default: Mistral / Voxtral (voxtral-mini-tts-latest). Default voice en_paul_neutral. Other presets include en_paul_happy, en_paul_sad, en_paul_excited, en_paul_frustrated, gb_oliver_neutral, gb_jane_sarcasm (expressive, multilingual).
OpenAI (gpt-4o-mini-tts), via --provider openai. Default voice coral (also marin, cedar, alloy, nova, etc.).
Gemini (gemini-3.1-flash-tts-preview), via --provider gemini. Default voice Kore (also Puck, Charon, Aoede, Zephyr, etc.). Outputs OGG/WAV. Slow preview model — prefer gemini:gemini-2.5-flash-preview-tts for speed/cost.
xAI Grok (grok-tts), via --provider xai. Default voice eve (also ara, leo, rex, sal). Cheapest + fast; supports inline speech tags like [laugh], [sigh], <whisper>. English by default.
Auto-detect prefers Mistral (MISTRAL_API_KEY), then OpenAI (OPENAI_API_KEY), then Gemini (GEMINI_API_KEY), then xAI (XAI_API_KEY). Gemini and xAI are opt-in via --provider.

Read the full file on GitHub · 83 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.

5d ago First seen · 83 lines · 86 tokens per session scan A f15fe376d646

Subscribe to this mod's changes

speech is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,207 once invoked, about $0.0004 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.

Creative and media

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens