Enable high-quality, local text-to-speech with cloned voices in your OpenClaw instance using OpenAI-compatible backends.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install local-openedai-tts
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install local-openedai-tts using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Local OpenAI-Compatible TTS?
This skill empowers developers to integrate local text-to-speech (TTS) engines into their AI agent workflows. By leveraging Openclaw Skills, you can transition from cloud-dependent TTS providers to self-hosted solutions such as openedai-speech. This transition allows for the use of advanced voice cloning technology while maintaining strict data privacy.
The core value of this skill lies in its ability to mimic the OpenAI TTS API structure, making it a drop-in replacement for existing systems. It is particularly effective for those using XTTS models to create personalized agent personalities that can communicate through various messaging platforms without incurring external API costs.
Local OpenAI-Compatible TTS Use Cases
- Replacing expensive cloud-based TTS services with private, self-hosted alternatives.
- Implementing custom cloned voices for unique AI agent personalities.
- Generating deterministic audio clips for automated testing and quality assurance.
- Exposing local speech synthesis services to secure private networks via Tailscale.
- Enhancing agent communication on platforms like Telegram and WhatsApp with high-quality audio files.
How Local OpenAI-Compatible TTS Works
- Redirect the OpenClaw environment variables to point the OpenAI base URL toward your local TTS service endpoint.
- Configure the internal message TTS settings to use the openai provider while specifying the local model and voice mapping.
- Validate the global configuration using the OpenClaw CLI to ensure all environment variables are correctly recognized.
- Verify that cloned voice assets are correctly mapped within the backend container configuration files.
- Execute a direct API request via curl to generate a test audio file, bypassing the chat interface for isolated debugging.
- Adjust network binding settings to ensure the TTS backend is accessible across the LAN or specific Tailscale interfaces if required.
Local OpenAI-Compatible TTS Setup
To configure your instance using Openclaw Skills, run the following commands in your terminal:
# Point OpenClaw to your local TTS backend
openclaw config set env.vars.OPENAI_BASE_URL http://127.0.0.1:19000/v1
# Configure the TTS provider and voice parameters
openclaw config set messages.tts.provider openai
openclaw config set messages.tts.openai.model tts-1-hd
openclaw config set messages.tts.openai.voice me
# Verify the updated configuration
openclaw config get messages.tts
Local OpenAI-Compatible TTS Data Schema & Taxonomy
The skill manages configuration through the OpenClaw CLI, affecting how the agent interacts with audio backends. The following parameters are essential for correct operation:
| Key | Purpose | Required |
|---|---|---|
OPENAI_BASE_URL |
The URL of the local openedai-speech or similar service. | Yes |
messages.tts.provider |
Must be set to openai to use the compatible local API. |
Yes |
messages.tts.openai.model |
The specific model (e.g., tts-1-hd) that supports cloning. |
Yes |
messages.tts.openai.voice |
The unique identifier for the cloned voice in your backend. | Yes |
speed |
Playback speed, though currently limited by schema constraints. | Optional |
Local OpenAI-Compatible TTS Advanced Features
- Support for XTTS voice cloning for high-fidelity, personalized audio output.
- CLI-based configuration management to avoid manual JSON editing and potential syntax errors.
- Direct backend verification workflows using Docker exec to inspect voice-to-speaker mappings.
- Multi-channel delivery support for sending generated speech files to external platforms like Telegram.
- Network isolation and exposure controls for secure access via Tailscale or local area networks.
SKILL.md
Loading
Related Openclaw Skills
Cloudflare Whisper Worker
A high-performance audio transcription skill leveraging Cloudflare Workers and the Whisper model for seamless speech-to-text conversion.
ShellPhone Gateway
A private WebSocket gateway that establishes a secure, self-hosted bridge between iOS devices and local AI agents.
Reformed Books Search
A specialized AI agent skill for searching and downloading Reformed Christian theology books and academic PDF resources.
Feishu Group Mention Responder
An automated interaction tool that enables AI agents to detect and respond to @mentions or direct messages within Feishu group chats.
Whisper Tailnet API
A dedicated tool for accessing a shared Whisper STT server over a private Tailnet using OpenAI-compatible endpoints.
ADHD Assistant
A comprehensive executive function support system designed to help users manage daily planning, task breakdown, and emotional regulation through evidence-based ADHD strategies.
Featured*
