A comprehensive developer toolkit for building, debugging, and optimizing SenseAudio text-to-speech integrations across multiple protocols.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install senseaudio-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 senseaudio-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 SenseAudio TTS?
The SenseAudio TTS skill provides a robust framework for developers to integrate advanced speech synthesis capabilities into their applications. By leveraging Openclaw Skills, developers can rapidly implement high-fidelity voice generation using the SenseAudio API, supporting everything from standard one-shot audio generation to complex, low-latency streaming sessions.
This skill streamlines the development of voice-enabled interfaces by providing structured workflows for the /v1/t2a_v2 and /ws/v1/t2a_v2 endpoints. Whether you are building a simple notification system or a real-time conversational AI, this integration ensures technical precision in handling hex audio decoding, voice parameter tuning, and event sequencing.
SenseAudio TTS Use Cases
- Generating one-shot audio files for static content using synchronous HTTP requests.
- Implementing low-latency, real-time speech streaming in web applications via SSE (Server-Sent Events).
- Building interactive voice agents that require bi-directional, incremental text-to-audio sessions over WebSockets.
- Troubleshooting and debugging TTS error codes and parameter mismatches in existing Openclaw Skills integrations.
- Optimizing voice selection and audio tuning for specific brand identities.
How SenseAudio TTS Works
- Protocol Selection: The agent evaluates the use case to choose between HTTP sync for simplicity, SSE for incremental chunks, or WebSocket for real-time interactivity.
- Request Construction: It builds a valid request payload including the required Auth headers, model selection, input text, and specific voice_id settings.
- Output Processing: The skill handles the raw API response, specifically decoding the
data.audiohex string into playable audio bytes. - Session Finalization: It monitors for terminal status events to ensure the audio stream or file generation is completed successfully.
- Error Handling: It implements robust logic to manage authentication failures and network retries for production-grade reliability.
SenseAudio TTS Setup
To get started with this skill, you must configure your environment with your SenseAudio credentials.
- Obtain an API key from the SenseAudio Platform.
- Export the environment variable in your terminal:
export SENSEAUDIO_API_KEY='your_api_key_here'
- Ensure your Openclaw Skills environment has access to this variable to authenticate requests to the
/v1/t2a_v2endpoints.
SenseAudio TTS Data Schema & Taxonomy
The skill organizes its operations around the following data structures:
| Component | Description |
|---|---|
| Headers | Requires Authorization bearer token using the SENSEAUDIO_API_KEY. |
| Payload | Contains model, text, and voice_setting (including voice_id). |
| Response | Data is returned as hex-encoded strings in the data.audio field. |
| Endpoints | /v1/t2a_v2 (HTTP/SSE) and /ws/v1/t2a_v2 (WebSocket). |
SenseAudio TTS Advanced Features
- Protocol Switching: Seamlessly move between SSE and WebSocket based on latency requirements.
- Hex-to-Byte Decoding: Built-in logic for handling raw audio data formats.
- Voice Tuning: Granular control over audio parameters for customized speech output.
- Production Hardening: Integrated patterns for exponential backoff and session tracing for enterprise-level Openclaw Skills deployments.
SKILL.md
Loading
Related Openclaw Skills
Voice2Notion
An automated voice transcription tool that uses faster-whisper to turn audio recordings into structured entries within a Notion database.
YouTube Video Category
A specialized skill for interacting with the YouTube API to retrieve and manage video category metadata via the yutu CLI.
Structured Workflow (Lightweight)
A lightweight, Chinese-first framework designed to enforce structured thinking, task decomposition, and concise communication for AI coding agents.
Stock Daily Report HK
An automated AI trading strategist that generates and delivers comprehensive Hong Kong stock market momentum reports to Feishu every trading day.
Research Analyzer
A comprehensive research and analysis tool powered by the Tavily API for intelligent web searching and structured report generation.
Writing Reboot Review
A structured analytical framework designed to help writers review past performance, diagnose burnout or blocks, and establish a sustainable content strategy.
Featured*
