ClawVoice

Integration Guide

REST API & OpenClaw plugin. Choose what fits your workflow.

REST API

For Web, App, backend—any HTTP client. Create an API Key in the Dashboard and start calling.

Request example

curl -X POST https://api.clawvoice.com/v1/tts/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello world",
    "emotion": "happy",
    "speed": 1.0
  }' \
  --output audio.wav

Parameters

ParamTypeRequiredDescription
textstringYesText to synthesize, max 5000 chars. Context-aware. 10+ languages: Chinese, English, Japanese, Korean, Cantonese, Sichuanese, etc.
voice_idstringNoVoice ID (from cloned voices). Omit to use first available voice.
emotionstringNohappy / sad / angry / calm / excited. Auto-selects instruct mode.
speednumberNo0.5–2.0, default 1.0

JavaScript

const res = await fetch('https://api.clawvoice.com/v1/tts/generate', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    text: 'Hello world',
    emotion: 'happy',
    speed: 1.2,
  }),
});
const blob = await res.blob();

Python

import requests

resp = requests.post(
    'https://api.clawvoice.com/v1/tts/generate',
    headers={'Authorization': 'Bearer YOUR_API_KEY'},
    json={'text': 'Hello world', 'emotion': 'neutral', 'speed': 1.0},
)
with open('output.mp3', 'wb') as f:
    f.write(resp.content)

OpenClaw Skill Plugin

Use ClawVoice TTS directly in OpenClaw. Get an API Key, install the skill, configure it, and synthesize speech in chat.

For OpenClaw users

  1. Get an API KeyCreate an API Key in the Dashboard.
  2. Install the skill

    Using ClawHub CLI (recommended):

    npx clawhub@latest install clawvoice-tts

    Or manually: download the openclaw-skill folder from our GitHub repo, then copy it to ~/.openclaw/skills/.

  3. Configure in OpenClaw

    Open OpenClaw → Settings → Skills → ClawVoice TTS. Enter your API Key and save.

  4. Use in chat

    In OpenClaw chat, ask the assistant to synthesize text to speech. For example: "Read this aloud" or "Convert this text to speech."

For developers

Manual install from source, CLI usage:

cd plugins/clawvoice-skill
pip install -r requirements.txt

# Set CLAWVOICE_API_KEY, then:
python main.py "Hello world" -o output.mp3
python main.py "Great day!" --emotion happy --speed 1.2 -o out.mp3

Ready to integrate?

DashboardPricing