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 (Cancan) 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 (general-purpose scenarios)
| Voice Name |
Voice Type |
Description |
| Shiny (Cancan) |
zh_female_cancan_mars_bigtts |
Cheerful female voice, suitable for various scenarios |
| Lively Xiaoning |
zh_female_wanwanxiaohe_mars_bigtts |
Lively and playful female voice |
| Xiaomo |
zh_male_xiaomo_mars_bigtts |
Warm and friendly male voice |
| Xiaoqi |
zh_female_xiaoqi_mars_bigtts |
Professional female host |
| AISuper (AI Super Fluent) |
zh_female_gaolanfenqu_mars_bigtts |
Super fluent female voice |
Emotional Category (ultra-natural emotional voices)
| Voice Name |
Voice Type |
Description |
| Happy Xiaodong |
zh_male_xudong_conversation_wvae_bigtts |
Cheerful and sunny male voice |
| Sad Xiaoliang |
zh_male_sadxiaoliang_sad_mars_bigtts |
Melancholic male voice |
| Neutral Xiaoshuai |
zh_male_zhongxingxiaoshuai_speech_mars_bigtts |
Neutral tone male voice |
| Happy Xiaomei |
zh_female_gaoxiaomei_happy_mars_bigtts |
Cheerful female voice |
| Angry Xiaotian |
zh_female_shengmoxiaotian_angry_mars_bigtts |
Angry tone female voice |
Intelligent Customer Service
| Voice Name |
Voice Type |
Description |
| Customer Service Xiaowen |
zh_male_jingyixiaowen_mars_bigtts |
Professional customer service male voice |
| Customer Service Xiaorou |
zh_female_xiaorou_customer_service_mars_bigtts |
Gentle customer service female voice |
Documentary
| Voice Name |
Voice Type |
Description |
| Classic Xiaoming |
zh_male_jingdianxiaoming_mars_bigtts |
Classic documentary male voice |
| Narration Xiaoran |
zh_female_xiaoran_narration_mars_bigtts |
Documentary narration female voice |
Audio Novels
| Voice Name |
Voice Type |
Description |
| Storytelling Xiaotao |
zh_female_jiangshuxiaotao_mars_bigtts |
Storytelling female voice |
| Warm Xiaochen |
zh_male_wennuanxiaochen_mars_bigtts |
Warm novel reading male voice |
News Broadcasting
| Voice Name |
Voice Type |
Description |
| News Xiaozhi |
zh_male_xinwenxiaozhi_mars_bigtts |
Standard news broadcasting male voice |
| News Xiaojing |
zh_female_xinwenxiaojing_mars_bigtts |
Professional news broadcasting female voice |
| Cantonese News |
zh_male_yueyuxiaowu_mars_bigtts |
Cantonese news male voice |
| Amoy News (Southern Min news) |
zh_female_minnanxiaoyue_mars_bigtts |
Amoy dialect news female voice |
General-Multilingual
| Voice Name |
Voice Type |
Description |
| English Gentle (gentle male English voice) |
en_male_mars_bigtts |
Gentle English male voice |
| English Lively (lively female English voice) |
en_female_mars_bigtts |
Lively English female voice |
| Japanese Male |
ja_male_mars_bigtts |
Japanese male voice |
| Japanese Female |
ja_female_mars_bigtts |
Japanese female voice |
| Korean Male |
ko_male_mars_bigtts |
Korean male voice |
| Korean Female |
ko_female_mars_bigtts |
Korean female voice |
| French Male |
fr_male_mars_bigtts |
French male voice |
| French Female |
fr_female_mars_bigtts |
French female voice |
| German Male |
de_male_mars_bigtts |
German male voice |
| German Female |
de_female_mars_bigtts |
German female voice |
| Spanish Male |
es_male_mars_bigtts |
Spanish male voice |
| Spanish Female |
es_female_mars_bigtts |
Spanish female voice |
| Russian Male |
ru_male_mars_bigtts |
Russian male voice |
| Russian Female |
ru_female_mars_bigtts |
Russian female voice |
| Portuguese Male |
pt_male_mars_bigtts |
Portuguese male voice |
| Portuguese Female |
pt_female_mars_bigtts |
Portuguese female voice |
| Italian Male |
it_male_mars_bigtts |
Italian male voice |
| Italian Female |
it_female_mars_bigtts |
Italian female voice |
| Arabic Male |
ar_male_mars_bigtts |
Arabic male voice |
| Arabic Female |
ar_female_mars_bigtts |
Arabic female voice |
| Hindi Male |
hi_male_mars_bigtts |
Hindi male voice |
| Hindi Female |
hi_female_mars_bigtts |
Hindi female voice |
| Thai Male |
th_male_mars_bigtts |
Thai male voice |
| Thai Female |
th_female_mars_bigtts |
Thai female voice |
| Vietnamese Male |
vi_male_mars_bigtts |
Vietnamese male voice |
| Vietnamese Female |
vi_female_mars_bigtts |
Vietnamese female voice |
| Indonesian Male |
id_male_mars_bigtts |
Indonesian male voice |
| Indonesian Female |
id_female_mars_bigtts |
Indonesian female voice |
| Malay Male |
ms_male_mars_bigtts |
Malay male voice |
| Malay Female |
ms_female_mars_bigtts |
Malay female voice |
| Filipino Male |
fil_male_mars_bigtts |
Filipino male voice |
| Filipino Female |
fil_female_mars_bigtts |
Filipino female voice |
| Turkish Male |
tr_male_mars_bigtts |
Turkish male voice |
| Turkish Female |
tr_female_mars_bigtts |
Turkish female voice |
| Dutch Male |
nl_male_mars_bigtts |
Dutch male voice |
| Dutch Female |
nl_female_mars_bigtts |
Dutch female voice |
| Polish Male |
pl_male_mars_bigtts |
Polish male voice |
| Polish Female |
pl_female_mars_bigtts |
Polish female voice |
| Ukrainian Male |
uk_male_mars_bigtts |
Ukrainian male voice |
| Ukrainian Female |
uk_female_mars_bigtts |
Ukrainian female voice |
| Hebrew Male |
he_male_mars_bigtts |
Hebrew male voice |
| Hebrew Female |
he_female_mars_bigtts |
Hebrew female voice |
Dialect Category (dialect scenarios)
| Voice Name |
Voice Type |
Description |
| Cantonese Male |
zh_male_yueyuzhongxing_mars_bigtts |
Cantonese male voice |
| Cantonese Female |
zh_female_yueyumars_mars_bigtts |
Cantonese female voice |
| Amoy Male (Southern Min male voice) |
zh_male_taiminmars_mars_bigtts |
Amoy dialect male voice |
| Amoy Female (Southern Min female voice) |
zh_female_minnanAImars_mars_bigtts |
Amoy dialect female voice |
| Sichuanese |
zh_male_sichuanmars_mars_bigtts |
Sichuan dialect male voice |
| Shanghainese |
zh_female_shanghaihuamars_mars_bigtts |
Shanghainese female voice |
| Wuhan Dialect |
zh_male_wuhanmars_mars_bigtts |
Wuhan dialect male voice |
| Hunan Dialect |
zh_male_hunanmars_mars_bigtts |
Hunan dialect male voice |
| Henan Dialect |
zh_female_henanmars_mars_bigtts |
Henan dialect female voice |
| Northeastern Dialect |
zh_male_dongbeimars_mars_bigtts |
Northeastern dialect male voice |
| Shandong Dialect |
zh_male_shandongmars_mars_bigtts |
Shandong dialect male voice |
| Tianjin Dialect |
zh_female_tianjinmars_mars_bigtts |
Tianjin dialect female voice |
Special Categories
| Voice Name |
Voice Type |
Description |
| Audiobook Xiaoyu |
zh_female_xiaoyujingxisanguo_mars_bigtts |
Three Kingdoms audiobook voice |
| Animation Xiaohua |
zh_female_xiaohuadongman_mars_bigtts |
Anime style voice |
| Rap Xiaoqiang |
zh_female_xiaoqiangrap_mars_bigtts |
Rap style female voice |
| RAP General (Rap Dajiang) |
zh_male_rapgeneral_mars_bigtts |
Rap style male voice |
| Wise Voice |
zh_male_jinyumars_mars_bigtts |
Wise and mature voice |
| Chattering |
zh_female_laolaodaodao_chat_mars_bigtts |
Chatty female voice |
| Talking Beijing |
zh_male_jianghuabeijing_speech_mars_bigtts |
Beijing accent |
| Host Xiaoyang |
zh_female_xiaoyang_host_mars_bigtts |
Streamer host style |
Output
The generated audio file will be saved to the specified output path (default: output.mp3 in current directory).
Notes
- Ensure VOLCANO_TTS_APPID, VOLCANO_TTS_ACCESS_TOKEN, and VOLCANO_TTS_SECRET_KEY environment variables are set
- Supports mp3, pcm, and wav formats (mp3 by default)
- Speed range: 0.8-2.0 (1.0 is normal)
- Volume range: 0.1-3.0 (1.0 is normal)
- Voice types can be viewed using
--list-voices
- Different clusters may support different voice types; default cluster is
volcano_tts
- For non-Chinese text, use multilingual voices from "General-Multilingual" category
