name: doubao-open-tts
description: Text-to-Speech using Doubao (Volcano Engine) API. Use when converting text to natural-sounding speech, generating audio files from text, listing available TTS voices, or synthesizing speech with customizable speed/volume parameters.

Doubao Open TTS

Text-to-Speech (TTS) service using Doubao (Volcano Engine) API V1 interface to convert text into natural-sounding speech.

Features

• 🎙️ 200+ Voice Options - Default: Shiny (灿灿) for general scenarios
• 🔊 Multiple Audio Formats - Supports mp3, pcm, wav
• ⚡ Adjustable Parameters - Speed and volume control
• 📦 Dual Interface - Command-line tool + Python API
• 🎯 Voice Categorization - Browse voices by category

Installation

cd skills/doubao-open-tts
pip install -r requirements.txt

Configuration

Method 1: 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"
export VOLCANO_TTS_VOICE_TYPE="zh_female_cancan_mars_bigtts"  # Optional: set default voice

Method 2: .env File

Copy .env.example.txt to .env and fill in your credentials:

cp .env.example.txt .env
# Edit the .env file with your credentials

Usage

Command Line

# Basic usage (uses default voice: Shiny)
python scripts/tts.py "Hello, this is a test of Doubao text-to-speech service"

# Specify output file and format
python scripts/tts.py "Welcome to use TTS" -o output.mp3 -e mp3

# Read text from file
python scripts/tts.py -f input.txt -o output.mp3

# Adjust parameters
python scripts/tts.py "Custom voice" --speed 1.2 --volume 0.8 -v zh_female_cancan_mars_bigtts

# List all available voices
python scripts/tts.py --list-voices

# List voices by category
python scripts/tts.py --list-voices --category "General-Multilingual"

# Use different cluster
python scripts/tts.py "Hello" --cluster volcano_tts

# Enable debug mode
python scripts/tts.py "Test" --debug

Python API

from scripts.tts import VolcanoTTS, VOICE_TYPES, VOICE_CATEGORIES

# Initialize client
tts = VolcanoTTS(
    app_id="your_app_id",
    access_token="your_access_token",
    secret_key="your_secret_key",
    voice_type="zh_female_cancan_mars_bigtts"  # Optional: set default voice
)

# List available voices
print("All voices:", tts.list_voices())
print("General voices:", tts.list_voices("General-Normal"))

# Change voice
tts.set_voice("zh_male_xudong_conversation_wvae_bigtts")  # Set to "Happy Xiaodong"

# Synthesize speech
output_path = tts.synthesize(
    text="Hello, this is Doubao text-to-speech",
    voice_type="zh_female_cancan_mars_bigtts",  # Optional: override default
    encoding="mp3",
    cluster="volcano_tts",
    speed=1.0,
    volume=1.0,
    output_file="output.mp3"
)
print(f"Audio saved to: {output_path}")

Available Voice Types

General Category (通用场景)

Emotional Category (情感超自然人声)

Intelligent Customer Service (智能客服)

Documentary (纪录片)

Audio Novels (有声小说)

News Broadcasting (新闻播报)

General-Multilingual (通用多语言)

Dialect Category (方言场景)

Special Categories

Output

The generated audio file will be saved to the specified output path (default: output.mp3 in current directory).

Notes

1. Ensure VOLCANO_TTS_APPID, VOLCANO_TTS_ACCESS_TOKEN, and VOLCANO_TTS_SECRET_KEY environment variables are set
2. Supports mp3, pcm, and wav formats (mp3 by default)
3. Speed range: 0.8-2.0 (1.0 is normal)
4. Volume range: 0.1-3.0 (1.0 is normal)
5. Voice types can be viewed using --list-voices
6. Different clusters may support different voice types; default cluster is volcano_tts
7. For non-Chinese text, use multilingual voices from "General-Multilingual" category