doubao-open-tts

Synthesize speech from text via the Doubao (Volcano Engine) API.

1|Updated Jan 30, 2026

Search Tags:#API #text-to-speech #Python #tts #audio-generation #voice-selection #VolcanoEngine

Ready to run

npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill doubao-open-tts

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: doubao-open-tts
Source: https://github.com/xdrshjr/JR-Agent-Skills/tree/main/doubao-open-tts
Command: npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill doubao-open-tts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This skill enables text-to-speech synthesis using the Doubao (Volcano Engine) API.

Core Features & Use Cases

Voice variety: Access 200+ voices across languages and tones for dynamic audio narration.
Flexible formats: Produce mp3, wav, or pcm audio to fit any integration.
Use cases: Narration for applications, video dubbing, e-learning, and accessibility features.

Quick Start

Install dependencies: pip install -r requirements.txt
Configure credentials: copy .env.example.txt to .env and set VOLCANO_TTS_APPID, VOLCANO_TTS_ACCESS_TOKEN, VOLCANO_TTS_SECRET_KEY, and optional VOLCANO_TTS_VOICE_TYPE
Run a quick synth: python scripts/tts.py "Hello, world" -o output.mp3

Frequently Asked Questions about doubao-open-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert text to speech using the Volcano Engine API in Python?▼

Text-to-speech synthesis with the Volcano Engine API uses Python 3 and the requests library to convert text into natural speech. You configure credentials in environment variables and run the script to generate audio.

What audio formats can I generate with Python text-to-speech scripts?▼

Python text-to-speech synthesis via the Volcano Engine API supports generating mp3, wav, and pcm audio formats. This flexibility allows you to produce audio files suited for applications, video dubbing, and accessibility features.

Do I need environment variables to use the Volcano Engine text-to-speech API?▼

Yes, Volcano Engine text-to-speech API authentication requires setting the VOLCANO_TTS_APPID, VOLCANO_TTS_ACCESS_TOKEN, and VOLCANO_TTS_SECRET_KEY environment variables. An optional VOLCANO_TTS_VOICE_TYPE variable can also be set to select a specific voice.

Can I adjust the speed and volume of generated speech for video dubbing?▼

Yes, text-to-speech synthesis using the Volcano Engine API supports adjusting both the speed and volume of the generated speech. This allows you to customize audio narration to fit your video dubbing and e-learning use cases.

How many voices are available for text-to-speech synthesis with the Volcano Engine API?▼

Text-to-speech synthesis with the Volcano Engine API provides access to over 200 voices across multiple languages and tones. This variety enables dynamic audio narration for diverse application and accessibility needs.