A robust AI agent skill for converting text into natural-sounding audio files using the Telnyx TTS API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install telnyx-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 telnyx-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 Telnyx Text-to-Speech?
The Telnyx Text-to-Speech skill enables AI agents to produce high-fidelity audio content directly from text inputs. By leveraging the Telnyx API, this tool provides developers with a streamlined way to integrate voice synthesis into their automation workflows. As part of the Openclaw Skills ecosystem, it bridges the gap between text-based AI processing and audible media generation, making it ideal for voice assistants and automated messaging systems.
Telnyx Text-to-Speech Use Cases
- Creating automated voice notifications for system alerts.
- Generating audio content for accessibility-focused applications.
- Sending voice notes automatically through Telegram using Openclaw Skills.
- Developing interactive voice response (IVR) prompts for communication platforms.
How Telnyx Text-to-Speech Works
- The user or agent provides a text string and optional parameters like voice ID or output path.
- The script sends the request to the Telnyx API using the configured credentials.
- Telnyx processes the text and returns a high-quality MP3 audio stream.
- The skill saves the audio file to the specified location and returns the file path for further processing within Openclaw Skills.
Telnyx Text-to-Speech Setup
Ensure you have python3 installed on your system. You must also obtain an API key from Telnyx to use this service with Openclaw Skills.
# Set the required environment variable
export TELNYX_API_KEY='your_api_key_here'
# Run the conversion script
./scripts/telnyx-tts.py "Hello World" -o /tmp/output.mp3
Telnyx Text-to-Speech Data Schema & Taxonomy
The skill processes text inputs and produces audio files. Below is the metadata and file structure used by these Openclaw Skills:
| Attribute | Description |
|---|---|
| Input | Raw text string |
| Output | MP3 audio file |
| Voice Options | NaturalHD (Premium) or KokoroTTS (Budget) |
| Environment | TELNYX_API_KEY required |
Telnyx Text-to-Speech Advanced Features
- Access to NaturalHD voices including astra, luna, and andersen_johan for superior prosody.
- Budget-friendly KokoroTTS models for high-volume automated voice generation.
- Automatic integration with Telegram voice note formatting within Openclaw Skills.
- Flexible command-line arguments for overriding default voice and output destinations.
SKILL.md
Loading
Related Openclaw Skills
Telnyx STT
A high-performance speech-to-text skill leveraging the Telnyx API and Whisper models to transcribe multiple audio formats into plain text.
Backup to Telnyx Storage
A streamlined CLI-based skill to automate the backup and restoration of OpenClaw workspace data to Telnyx S3-compatible storage.
Telnyx Network
A networking skill for creating private WireGuard meshes and exposing services via Telnyx infrastructure.
Telnyx Freemium Upgrade
Automatically transitions Telnyx accounts from freemium restrictions to professional tier capabilities using social identity verification.
SIP Voice Call Control
A SIP-based voice interface that enables natural phone conversations with your AI assistant using the Telnyx Call Control API.
vvvv gamma Channels C# Integration
A comprehensive integration for managing vvvv gamma's reactive channel system directly through C# code and AI agents.