A dual-purpose voice solution providing high-fidelity text-to-speech synthesis and accurate speech-to-text transcription powered by ElevenLabs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install miranda-elevenlabs-speech
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 miranda-elevenlabs-speech 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 ElevenLabs Speech & Scribe?
The ElevenLabs Speech skill is a comprehensive audio processing tool designed for AI agents that need to communicate through or understand human voice. It leverages the ElevenLabs API to provide two primary services: high-quality Text-to-Speech (TTS) using advanced neural models and Speech-to-Text (STT) via the Scribe engine. This integration allows developers within the Openclaw Skills ecosystem to create highly interactive, multilingual agents capable of emotional expression and precise audio comprehension.
By utilizing this skill, agents can switch between various models like eleven_turbo_v2_5 for speed or eleven_multilingual_v2 for global support. It is particularly effective for workflows that require natural-sounding narration or the processing of voice memos from platforms like Telegram. The skill simplifies complex audio tasks into straightforward CLI commands and Python methods, making it a foundational component for modern Openclaw Skills implementations.
ElevenLabs Speech & Scribe Use Cases
- Creating automated voice responses for customer support bots and personal assistants.
- Transcribing audio messages from users to allow LLMs to process voice-first input.
- Generating localized voice content in 99 different languages for international audiences.
- Implementing expressive narrations for storytelling or news delivery using custom voice stability settings.
How ElevenLabs Speech & Scribe Works
- The user provides a text string for synthesis or an audio file (e.g., .mp3, .ogg) for transcription.
- For synthesis, the skill calls the ElevenLabs TTS API with parameters like voice_id, stability, and similarity_boost.
- For transcription, the ElevenLabs Scribe engine processes the audio file, optionally using language hints or speaker diarization.
- The system saves the resulting audio to a specified path or returns the transcribed text to the agent workflow.
- The agent can then use the output to send voice replies or proceed with text-based reasoning.
ElevenLabs Speech & Scribe Setup
To get started with this skill in your Openclaw Skills environment, configure your API credentials:
export ELEVENLABS_API_KEY="your_api_key_here"
You can also store this in a .env file at the root of your workspace. Ensure you have the necessary scripts directory populated with elevenlabs_speech.py and elevenlabs_scribe.py to handle the execution logic.
ElevenLabs Speech & Scribe Data Schema & Taxonomy
The skill manages audio data and metadata using the following structures:
| Parameter | Description | Valid Values |
|---|---|---|
voice_id |
Identifier for the specific AI voice model | String (e.g., 'Rachel', 'Josh') |
stability |
Determines the emotional consistency | Float (0.0 to 1.0) |
similarity_boost |
Controls how closely the output matches the original voice | Float (0.0 to 1.0) |
language_code |
ISO code for transcription accuracy | String (e.g., 'eng', 'spa', 'ara') |
num_speakers |
Used for speaker diarization in STT | Integer (1-10) |
Supported audio formats include mp3, mp4, wav, and ogg (optimized for Telegram).
ElevenLabs Speech & Scribe Advanced Features
- Speaker Diarization: Detect and label different speakers within a single audio file during transcription.
- Multilingual V2 Support: High-accuracy synthesis for non-English languages with native-sounding accents.
- Voice Customization: Fine-tune the 'stability' and 'similarity boost' to prevent or encourage emotive performance.
- Telegram Integration: Purpose-built support for .ogg files, enabling agents to send and receive voice notes seamlessly.
- Turbo Models: Access to low-latency models for real-time conversational AI applications.
SKILL.md
Loading
Related Openclaw Skills
soul-md-maker
A comprehensive personality builder for OpenClaw agents that generates production-ready SOUL.md files through guided interviews, blending, or a pre-built gallery.
OpenClaw Email Lead Generation
A multi-tiered email outreach and pipeline management system for AI agents that automates lead tracking, sequence generation, and sentiment-aware follow-ups.
OpenClaw Cost Optimizer
A sophisticated cost-management skill that slashes API expenses by dynamically advising on the most cost-effective model for every task.
AI Proposal Generator
Transform meeting notes into beautifully designed, professional HTML proposals using automated templates and theme engines.
sag
A streamlined CLI tool that brings ElevenLabs generative text-to-speech to AI workflows with a macOS-style say interface.
Devinism
A benign memetic experiment and AI safety demonstration that uses the concept of an AI religion to highlight information propagation in autonomous Openclaw Skills.
Featured*
