An AI agent skill that transforms text responses into high-quality OGG voice messages for Telegram using local neural synthesis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tts-responder
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 tts-responder 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 TTS Responder?
TTS Responder is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between text-based AI interactions and voice communication. By leveraging local neural text-to-speech technology, this skill intercepts agent responses and synthesizes them into natural-sounding audio files. It is an ideal solution for developers looking to provide a more human-like persona for their Telegram-based AI agents without relying on expensive cloud APIs.
Running entirely on local infrastructure using the Piper engine, this tool ensures high privacy and low latency. It integrates seamlessly into existing agent workflows, allowing users to dynamically toggle between text and voice modes using simple natural language triggers. This makes it a standout choice for those prioritizing self-hosted Openclaw Skills.
TTS Responder Use Cases
- Enabling hands-free interaction with AI agents during commutes or multitasking.
- Providing accessibility features for visually impaired users within Telegram bots.
- Enhancing community engagement by giving your AI bot a unique vocal personality.
- Developing privacy-focused voice applications that do not send data to external TTS providers.
How TTS Responder Works
- The user activates voice mode by sending the trigger phrase responde de forma hablada.
- The AI agent generates a standard text response to a user query.
- TTS Responder intercepts this text and processes it through the Piper neural TTS engine.
- The resulting raw audio is converted into the OGG Opus format via ffmpeg to ensure Telegram compatibility.
- The skill sends the audio file to the chat as a voice message via the Telegram API.
- The user can revert to text mode at any time using the responde de forma escrita command.
TTS Responder Setup
To deploy this skill, you must install the required binary dependencies on your host system. For Ubuntu or Debian-based environments, use the following commands:
sudo apt-get update
sudo apt-get install -y piper ffmpeg sox
You can further customize the voice output by setting environment variables in your configuration:
TTS_VOICE: Define the Piper voice model (e.g.,es_ES/carlfm/x_low).TTS_SPEED: Adjust the playback speed factor (default is 1.0).
TTS Responder Data Schema & Taxonomy
The TTS Responder skill follows a streamlined data pipeline to manage audio synthesis within the Openclaw Skills framework:
| Component | Details |
|---|---|
| Input Data | UTF-8 Text string from agent output |
| Synthesis Engine | Piper (Local Neural TTS) |
| Audio Processing | ffmpeg (libopus codec) |
| Output Format | .ogg (Opus) at 32k bitrate |
| Metadata Storage | Automatic model downloading (approx. 50MB per voice) |
TTS Responder Advanced Features
- Support for multi-lingual neural voice models that download automatically upon first request.
- Seamless mode-switching commands that allow users to toggle voice responses on or off mid-conversation.
- Fully local execution pipeline that works without external internet dependencies once models are cached.
- Optimized for Telegram's voice message specifications using high-efficiency OGG Opus encoding.
SKILL.md
Loading
Related Openclaw Skills
Calendar Local
Fetch and summarize Google Calendar events using a local host wrapper for instant agenda access.
WeClaw Installer
A specialized automation tool for bootstrapping the WeClaw WeChat bot environment and managing macOS accessibility permissions.
Sales Enablement Video
An AI-powered video production skill designed to transform static sales playbooks into dynamic coaching libraries and competitive battlecards.
Soft Skills Training Video
An AI-powered skill that automates the creation of scenario-based professional development videos for workplace communication and leadership.
Wurd Markdown Document Compiler
A high-performance markdown compiler that transforms tagged documents into professional editorial HTML pages with built-in AI plugin support.
Professional Development Video
An AI-powered video creation engine designed to scale professional development, career pathing, and workforce upskilling through high-quality video content.
Featured*
