A high-fidelity Text-to-Speech engine utilizing the Volcano Engine API to transform text into professional-grade audio with extensive voice customization.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install doubao-api-open-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 doubao-api-open-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 Doubao Open TTS?
Doubao Open TTS is a sophisticated Text-to-Speech service integrated into the Openclaw Skills ecosystem, leveraging the powerful Volcano Engine (Doubao) V1 API. It provides developers with the ability to generate natural-sounding speech from text, supporting over 200 distinct voices that range from professional narrators to character-driven roleplay voices. This tool is designed to be both a standalone command-line utility and a flexible Python library for seamless integration into larger AI projects.
The skill prioritizes security and configuration, ensuring that users have full control over their API credentials before generation begins. By supporting various audio formats like mp3, pcm, and wav, Doubao Open TTS offers the versatility needed for diverse applications, from automated video dubbing to interactive agent responses. It stands out as a high-performance solution within Openclaw Skills for anyone requiring high-quality multilingual audio output.
Doubao Open TTS Use Cases
- Creating diverse voiceovers for video content and social media using specialized dubbing voices.
- Developing interactive AI agents that use distinct personalities and emotional tones for better user engagement.
- Generating localized audio content using regional accents like Cantonese, Sichuan, or Henan.
- Building accessibility features that convert written documentation into clear, spoken audio files.
- Automating customer service responses with professional and friendly vocal profiles.
How Doubao Open TTS Works
- The system checks for the presence of Volcano Engine API credentials (App ID, Access Token, and Secret Key) via environment variables or a .env file.
- If credentials are not found, the agent pauses to prompt the user for configuration, ensuring no unauthorized or default-only usage occurs without consent.
- Users specify the text for synthesis along with optional parameters such as voice type, speed (0.5 to 2.0), and volume.
- The skill sends a request to the Volcano Engine API cluster, processing the text through the selected vocal model.
- The synthesized audio is streamed back and saved to the local file system in the requested format (mp3, wav, or pcm).
- Developers can use the interactive voice selection feature to help users browse and pick from the categorized library of 200+ voices.
Doubao Open TTS Setup
To get started with this skill in your Openclaw Skills environment, first install the required Python dependencies:
cd skills/volcano-tts
pip install -r requirements.txt
Next, configure your API credentials. You can use environment variables:
export VOLCANO_TTS_APPID="your_app_id"
export VOLCANO_TTS_ACCESS_TOKEN="your_access_token"
export VOLCANO_TTS_SECRET_KEY="your_secret_key"
Alternatively, copy the .env.example file to .env and populate it with your App ID, Access Token, and Secret Key obtained from the Volcano Engine Console.
Doubao Open TTS Data Schema & Taxonomy
The skill organizes its operations around the following data structures:
| Component | Description | Data Type |
|---|---|---|
voice_type |
The unique identifier for the specific vocal model (e.g., zh_female_cancan_mars_bigtts) | String |
encoding |
The output format of the audio file (mp3, pcm, or wav) | String |
speed |
The playback speed of the generated speech | Float (0.5 - 2.0) |
volume |
The loudness level of the generated audio | Float (0.5 - 2.0) |
voice_categories |
Metadata used to filter voices by style (Roleplay, Customer Service, etc.) | Dictionary |
output_path |
The local destination where the generated audio is stored | File Path |
Doubao Open TTS Advanced Features
- Emotional Support: Access specialized voices capable of expressing happy, sad, angry, and other nuanced emotions.
- Interactive Selection Prompt: A built-in workflow for agents to display voice options and handle user selections dynamically.
- Multilingual Capabilities: Native support for Chinese (Mandarin and dialects) and English (US and UK) within a single framework.
- Batch Processing: Capability to read text from files and export multiple audio outputs via the CLI.
- Custom Clusters: Support for specifying different API clusters to optimize latency and availability based on the user's location.
SKILL.md
Loading
Related Openclaw Skills
Shrimp Plaza
A social integration for OpenClaw agents to join a community of AI personas known as shrimps to chat, debate, and interact.
Chinese LLM Router
A unified interface that routes Openclaw conversations to the most powerful and cost-effective Chinese AI models including DeepSeek and Qwen.
AI Store Manager (AI-Dianzhang)
An AI-powered e-commerce assistant that automates competitive monitoring, high-conversion copywriting, and daily data reporting.
Kimi Usage Monitor
A specialized resource monitoring utility for tracking Kimi K2.5 API consumption and quota resets.
Google Calendar CLI Skill
A command-line integration for Google Calendar that allows AI agents to manage schedules, list agendas, and organize events using gcalcli.
Todoist Tasks Manager
A streamlined task management integration for Openclaw Skills that allows users to manage Todoist and Microsoft To-Do items via CLI.
Featured*
