A speech toolkit that turns text into audio, turns recordings into text, and creates a custom copy of a speaker’s voice using Google services.

Use it to make voiceovers, transcribe audio, or create a custom voice from a clear reference recording and consent recording.

It provides one workflow for generating spoken audio, transcribing speech, and preparing voice-cloning requests with the required recordings and consent.

speech-use — Skill for Claude Code and Codex by cnemri

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 cnemri/google-genai-skills --skill speech-use

Clone the repo

git clone --depth 1 https://github.com/cnemri/google-genai-skills

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/cnemri/google-genai-skills/speech-use/github.svg)](https://agentmods.dev/skills/cnemri/google-genai-skills/speech-use)

Your own site

<a href="https://agentmods.dev/skills/cnemri/google-genai-skills/speech-use"><img src="https://agentmods.dev/badge/skills/cnemri/google-genai-skills/speech-use/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/cnemri/google-genai-skills/speech-use"><img src="https://agentmods.dev/badge/skills/cnemri/google-genai-skills/speech-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 665 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	$0.00042	$0.00665
Opus 5.5	$0.00017	$0.00266
Sonnet 5.5	$0.00008	$0.00133
Haiku 4.5	$0.00004	$0.00067

Measured 2mo ago against content hash e7e9659174f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

speech-use 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/create_custom_voice.py, scripts/generate_speech.py, scripts/transcribe_audio.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/speech-use/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speech Use

Use this skill to perform Text-to-Speech (TTS), Speech-to-Text (STT), and Voice Cloning operations.

This skill uses portable Python scripts managed by uv.

Prerequisites

Environment Variables:
- GOOGLE_API_KEY (for TTS via Gemini)
- GOOGLE_CLOUD_PROJECT (Required for STT and Voice Cloning)
- GOOGLE_APPLICATION_CREDENTIALS (Recommended for STT/Voice Cloning)
APIs Enabled:
- Text-to-Speech API (texttospeech.googleapis.com)
- Speech-to-Text API (speech.googleapis.com)

Usage

1. Generate Speech (TTS)

Generate audio from text using Gemini-TTS.

Standard Voice:

uv run skills/speech-use/scripts/generate_speech.py "Hello world, this is a test." --voice Puck --output hello.wav

Custom Voice (Cloned):

uv run skills/speech-use/scripts/generate_speech.py "This is my custom voice speaking." --voice-cloning-key "YOUR_KEY_HERE" --output custom.wav

2. Create Custom Voice (Voice Cloning)

Generate a voiceCloningKey from a reference audio file and a consent file.

Requirements:

reference.wav: 10-30s of clear speech (the voice to clone).
consent.wav: The speaker saying: "I am the owner of this voice and I consent to Google using this voice to create a synthetic voice model."

uv run skills/speech-use/scripts/create_custom_voice.py --reference-audio reference.wav --consent-audio consent.wav

Save the output key to use with generate_speech.py.

3. Transcribe Audio (STT)

Transcribe audio files using Chirp 3.

uv run skills/speech-use/scripts/transcribe_audio.py audio.wav --language en-US --output transcript.txt

Options

generate_speech.py

--voice: Prebuilt voice (e.g., Kore, Puck, Fenrir, Aoede).
--voice-cloning-key: Key from create_custom_voice.py.
--model: Default gemini-2.5-flash-preview-tts.

transcribe_audio.py

--model: Default chirp_3.
--language: Default auto.
--location: Cloud region (default us).

Read the full file on GitHub · 76 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.

2mo ago First seen · 76 lines · 42 tokens per session scan A e7e9659174f3

Subscribe to this mod's changes

speech-use is a skill published in the GitHub repository cnemri/google-genai-skills (129 stars, last pushed 9mo ago), licensed MIT. It adds 42 tokens to every session and 665 once invoked, about $0.0002 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 2026-08-30.

Creative and media

speech-use next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
speech-usecnemri/google-genai-skills	Skill	129	9mo ago	MIT	A	42	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code