A professional-grade text-to-speech engine powered by Volcano Engine, offering 34 distinct voices with advanced emotional expression and multi-format output.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install seedtts2
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 seedtts2 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 SeedTTS 2.0?
SeedTTS 2.0 is a sophisticated voice synthesis integration designed for the Openclaw Skills ecosystem. It leverages the Volcano Engine Doubao TTS 2.0 framework to deliver lifelike audio generation across 34 unique voices, covering Chinese and English, male and female tones, and specialized role-playing personas. This skill is optimized for developers who require high-fidelity audio (up to 24kHz) for AI agents, virtual assistants, or content creation workflows.
Beyond basic text conversion, this skill provides nuanced control over speech delivery through emotional tags. Users can specify moods such as gentle, happy, or serious directly within the text, allowing for a more human-like interaction. Whether you are building a JARVIS-inspired assistant or a professional narration tool, SeedTTS 2.0 provides the necessary SDK and CLI flexibility to integrate high-quality speech into any project.
SeedTTS 2.0 Use Cases
- Creating immersive AI assistants with the iconic JARVIS-style male voice.
- Generating localized audio content in both English (US/UK) and Mandarin Chinese.
- Automating batch audio production for storytelling or educational videos using the Python SDK.
- Integrating expressive emotional responses into customer service bots or gaming NPCs.
- Quick text-to-speech testing and playback directly from the terminal.
How SeedTTS 2.0 Works
- The user provides text input via the CLI or Python SDK, optionally including emotional markers like [gentle].
- The skill authenticates with the Volcano Engine API using configured APP ID and Access Token credentials.
- The SeedTTS 2.0 engine processes the text, applying the selected speaker profile and emotional nuances.
- High-quality audio is synthesized at a 24kHz sampling rate in MP3 or WAV format.
- The resulting file is saved to the local directory or played back immediately through the system's audio interface.
SeedTTS 2.0 Setup
Install the skill using the Openclaw Skills manager:
clawhub install seedtts2
Configure your Volcano Engine credentials via environment variables:
export VOLCANO_APP_ID="your_app_id"
export VOLCANO_ACCESS_TOKEN="your_access_token"
Alternatively, add the configuration to your Openclaw config file at ~/.openclaw/openclaw.json.
SeedTTS 2.0 Data Schema & Taxonomy
The skill manages audio assets and configuration through a structured directory and JSON schema:
| File/Folder | Description |
|---|---|
bin/seedtts2 |
Main executable for CLI operations |
tts_client.py |
Python SDK for programmatic integration |
examples/ |
Sample scripts for batch generation and emotion control |
output/ |
Default directory for generated MP3/WAV files |
Audio requests can be customized with parameters such as speaker (ID string), output (file path), and text (content with tags).
SeedTTS 2.0 Advanced Features
- Emotional Tagging: Inject expressions like [Happy] or [Serious] to alter the synthesized prosody.
- Batch Processing: Generate multiple audio files from a list of text strings in a single execution.
- Integrated Playback: Use the
-pflag in CLI to instantly hear the synthesized results. - Multi-lingual Support: Seamlessly switch between standard American English, British English, and various Chinese dialects.
- Custom Speaker Library: Access 34 specialized voices including 'Elegant Yichen' and 'Vivi 2.0'.
SKILL.md
Loading
Related Openclaw Skills
Markdown to PDF
A professional conversion tool that transforms Markdown text into high-quality PDF documents with syntax highlighting and custom styling support.
Ghost Integration for AI Agents
A powerful skill that enables AI agents to manage Ghost CMS content, members, and newsletters through the Membrane ecosystem.
Literary Fiction Craft
A professional-grade creative writing and developmental editing skill designed to help literary fiction authors refine narrative craft, tension, and prose.
1688 Supplier Search
A powerful sourcing agent that finds 1688 suppliers and factories using keywords, image URLs, or product links via the AlphaShop API.
Podcast Gen
An automated podcast generator that scrapes the latest news, writes oral-friendly scripts, and synthesizes high-quality audio using semantic voice matching.
Downloader
A streamlined automation skill designed to download and store remote resources from any HTTP/HTTPS URL directly to a local directory.
Featured*
