A high-fidelity text-to-speech engine powered by large language models to generate natural, emotionally expressive audio.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install text2speech
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 text2speech 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?
SenseAudio TTS is a sophisticated speech synthesis skill designed for the Openclaw Skills ecosystem, utilizing a large language model with billions of parameters. It converts written text into natural-sounding speech with support for over 10 different emotions and fine-grained control over voice characteristics. This skill provides developers with a robust API for creating high-quality audio content, offering both synchronous processing and low-latency SSE streaming modes to suit various application needs.
SenseAudio TTS Use Cases
- Creating natural-sounding voiceovers for digital content using Openclaw Skills.
- Building interactive AI assistants with realistic emotional expression.
- Reading technical documentation containing complex LaTeX or MathML formulas.
- Implementing real-time audio responses for streaming applications.
- Developing multi-language accessibility tools for Chinese and English speakers.
How SenseAudio TTS Works
- The user sends a POST request to the SenseAudio API with the text to be synthesized and configuration settings.
- The system analyzes the text, processing special tags like the break tag for pauses and mathematical notation.
- The large language model generates audio data based on the specified voice ID, speed, volume, and pitch.
- Audio is returned as hex-encoded data, either as a single response or a stream of chunks via Server-Sent Events.
- The client application decodes the hex string into a standard audio file format such as MP3 or WAV for playback.
SenseAudio TTS Setup
To integrate this skill into your Openclaw Skills workflow, you must obtain an API key from SenseAudio and configure your environment.
export SENSEAUDIO_API_KEY="your_senseaudio_api_key_here"
The skill authenticates via a Bearer token in the request header and targets the https://api.senseaudio.cn/v1/t2a_v2 endpoint.
SenseAudio TTS Data Schema & Taxonomy
The skill utilizes a structured JSON schema for requests and responses to ensure precise audio control.
| Object | Fields |
|---|---|
| voice_setting | voice_id, speed (0.5-2.0), vol (0-10), pitch (-12-12), latex_read (boolean) |
| audio_setting | format (mp3/wav/pcm/flac), sample_rate, bitrate, channel |
| Response Data | audio (hex-encoded), status, audio_length, word_count, usage_characters |
| Break Tag | Use <break time=500> within the text string to insert pauses in milliseconds. |
SenseAudio TTS Advanced Features
- Server-Sent Events (SSE) support for real-time, low-latency audio streaming.
- Advanced mathematical formula support allowing the AI to read LaTeX and MathML natively.
- Fine-tuned emotion control with over 10 distinct emotional profiles supported by the model.
- Precision control over speech mechanics, including multi-level pitch and volume adjustments.
- Custom dictionary support for polyphonic character corrections to improve pronunciation accuracy in specific contexts.
SKILL.md
Loading
Related Openclaw Skills
SenseAudio Voice Memo Transcriber
An intelligent transcription tool that converts spoken memos into categorized text with automatic extraction of dates, tasks, and contacts.
Email Drip Sequence Builder
A professional-grade AI tool for generating complete, ESP-ready email drip sequences from simple product descriptions.
Traffic Query
A specialized tool for querying and normalizing domestic China travel information for flights and trains.
TensorsLab Video Generation
A sophisticated AI video generation skill that converts text prompts and static images into cinematic content via the TensorsLab API.
BTC Signals Pro
BTC Signals Pro provides institutional-grade Bitcoin trading intelligence and AI-driven market signals for automated bots and professional traders.
Privacy Guard
A security-focused skill that prevents sensitive data leakage by performing deep content inspection on files before they are accessed or transmitted by an AI agent.
Featured*
