What is gemini-speech?

A text-to-speech tool that turns written text or a two-person dialogue into WAV audio using Gemini. Text-to-speech means generating spoken audio from words rather than recording a person.

Use it for voiceovers, audiobook passages, explainers, advertisements, announcements, and two-speaker podcast or dialogue audio.

It removes the need to record every voiceover, narration, announcement, or dialogue manually. Voice choice and delivery style can be adjusted and regenerated.

gemini-speech — Skill for Claude Code by mordor-forge/gemini-media-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.

Any agent

npx skills add mordor-forge/gemini-media-mcp --skill gemini-speech

Clone the repo

git clone --depth 1 https://github.com/mordor-forge/gemini-media-mcp

Made for: Claude Code.

Or install gemini-media, the plugin that ships this one along with the rest of its 5 skills.

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/mordor-forge/gemini-media-mcp/gemini-speech/github.svg)](https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/gemini-speech)

Your own site

<a href="https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/gemini-speech"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/gemini-speech/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mordor-forge/gemini-media-mcp/gemini-speech"><img src="https://agentmods.dev/badge/skills/mordor-forge/gemini-media-mcp/gemini-speech.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,620 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00142	$0.02620
Opus 5.5	$0.00057	$0.01048
Sonnet 5.5	$0.00028	$0.00524
Haiku 4.5	$0.00014	$0.00262

Measured 3d ago against content hash 7e685245524f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-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 3d 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.

skills/gemini-speech/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gemini Speech (TTS)

Quick start

Get the exact words to speak. If you are writing them, write for the ear (see below).
Choose a voice (default Aoede) and a short delivery style, e.g. "warm, unhurried documentary narrator".
Call gemini-media:generate_speech with text, voice and style.
The result is a WAV file (file.path, file.uri) with durationSeconds. Check the duration matches the script (roughly 2.5 words per second at a normal pace).
Adjust style, voice or the wording and regenerate as needed.

Tools

The tools live on the gemini-media MCP server. Harnesses name MCP tools differently (mcp__gemini-media__generate_speech, gemini-media.generate_speech, or plain generate_speech); match on the part after the server name. This skill writes them as gemini-media:<tool>.

Tool	Use it to
`gemini-media:generate_speech`	Synthesize one voice (`text`) or a two-speaker conversation (`dialogue`)
`gemini-media:list_models`	Current speech models and prices; `detail: true` lists all voices
`gemini-media:estimate_cost`	Price a long script (`mediaType: "speech"`, `text`)
`gemini-media:get_usage`	Spend so far and budget remaining

The one rule: text is spoken verbatim

The default model (tts, Gemini 3.8 Flash TTS) and tts-lite read text exactly as written. Anything you put there is spoken.

Sustained delivery (tone, pace, emotion, accent, character) goes in style, or per line in dialogue[].style. Never write "Say cheerfully:", "(whispering)", "Narrator:" or stage directions in text.
Point-in-time sounds go inline in text as angle-bracket tags at the exact spot: <sigh>, <laugh>, <chuckle>, <breath>, <gasp>, <cough>, <short pause>, <long pause>. Full list in references/voices.md.
Pacing: punctuation (..., --, commas), pause tags, or a style like "speaking slowly".
Emphasis: capitalize the stressed word: "This is a VERY important point."
Always use style even with legacy models (tts-2.5, tts-3.1, tts-pro): the server converts it into the directions those models expect.

Read the full file on GitHub · 144 lines

Files

What ships with it

4 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.

3d ago First seen · 144 lines · 142 tokens per session scan A 7e685245524f

Subscribe to this mod's changes

gemini-speech is a skill published in the GitHub repository mordor-forge/gemini-media-mcp (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 142 tokens to every session and 2,620 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-08.

Creative and media

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

systematic-debugging

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

obra/superpowers · 21 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

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

component-fixtures

Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.