devtools

openai_tts

Name: openai_tts
Author: sfortis

Text-to-speech for Home Assistant from OpenAI, Mistral, Groq, Lemonfox, Kokoro, Chatterbox or any server that implements the OpenAI speech API, with announcements that restore your volume and music.

221 stars56 forksPythonUpdated 10/11/2026100% free · open source

What it does

Adds a Home Assistant TTS platform that uses OpenAI’s speech API (or any compatible endpoint) to read out messages on your speakers.

When to use it

•You want dynamic voice alerts (e.g., “Package delivered”) without paying for a separate TTS service.
•You need high‑quality, natural‑sounding speech for smart‑home automations.
•You already have an OpenAI API key and want to keep everything inside Home Assistant.

Ready-to-paste prompt

service: tts.openai_say
entity_id: media_player.kitchen
message: "Hey, the oven pre‑heat is complete and the kitchen lights are set to 50 percent."

Heads up: The component will fail to load if the OpenAI API key does not have access to the `speech` (text‑to‑speech) endpoint or if you hit the usage quota – make sure you enable the “Audio” capability in your OpenAI account and have enough credits.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/openai-tts && curl -fsSL https://workflowstacks.com/api/skills/openai-tts/claude-skill -o ~/.claude/skills/openai-tts/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How openai_tts works

Codeflow

Free to inspect

Openai_tts is a medium Python project (~14k lines across 29 code files, plus 9 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit this month, GPL-3.0 license, has a test suite.

Size

Medium codebase

~14k lines · 29 code files · ~2 h to skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes

What's in each folder

custom_components/Folder42 files

tests/Tests — proof it works9 files

.github/CI / automation (GitHub Actions)2 files

READMEHas testsThin docsCI checksGPL-3.0 licenseUpdated this month