skills.rest
47thtechcorner
47thtechcornerCOMMUNITY
Explore all skills by this author →
GitHub

doubao-tts

Generate Mandarin and multilingual audio narration with word-level timing metadata via the Volcengine Doubao Speech 2.0 API.

21|9|Updated Jun 22, 2026
Search Tags:#subtitles#audio#tts#voiceover#doubao#mandarin
One-click install
npx skills add https://github.com/47thtechcorner/RayCodes_OpenMontage --skill doubao-tts-47thtechcorner
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doubao-tts
Source: https://github.com/47thtechcorner/RayCodes_OpenMontage/tree/main/openmontage_engine/.agents/skills/doubao-tts
Command: npx skills add https://github.com/47thtechcorner/RayCodes_OpenMontage --skill doubao-tts-47thtechcorner

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of generating high-quality, natural-sounding Mandarin and multilingual narration for video projects while ensuring precise subtitle synchronization.

Core Features & Use Cases

  • High-Fidelity TTS: Leverages Volcengine Doubao Speech 2.0 for professional-grade voice synthesis.
  • Subtitle Metadata: Provides character-level timestamp metadata, enabling perfectly synced captions.
  • Use Case: Use this when creating educational explainers or cinematic video content where you need natural voice pacing and accurate, phrase-grouped subtitles.

Quick Start

Use the doubao-tts skill to generate a voiceover for the provided script using the default female voice and enable timestamp metadata for subtitles.

Frequently Asked Questions about doubao-tts

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

FAQPage Schema
How do I generate Mandarin voiceovers with precise subtitle timestamps for video production?▼

You can generate Mandarin voiceovers with precise subtitle timestamps by using a TTS skill that synthesizes audio via the Volcengine Doubao Speech 2.0 API and outputs word-level timing metadata for exact caption synchronization.

Can I use Volcengine Doubao Speech 2.0 for multilingual narration in educational explainers?▼

Yes, Volcengine Doubao Speech 2.0 supports high-fidelity multilingual narration, making it suitable for educational explainers where natural voice pacing and accurate subtitles are required.

Do I need an API key to generate audio narration and subtitle metadata with Doubao TTS?▼

Yes, generating audio narration and subtitle metadata requires a valid DOUBAO_SPEECH_API_KEY to authenticate your requests with the Volcengine Doubao Speech 2.0 API.

How does word-level timestamp metadata work for syncing subtitles to synthesized speech?▼

Word-level timestamp metadata works by providing exact start and end times for each synthesized word, enabling you to align and group subtitle text perfectly with the corresponding audio narration.

What is the best way to integrate TTS audio generation into an OpenMontage video workflow?▼

The best way to integrate TTS audio generation into an OpenMontage video workflow is by using a skill designed to interface with the OpenMontage TTS selector module, providing both audio files and timing metadata.

Are there limitations when using Doubao TTS for professional cinematic video content?▼

A key limitation is that Doubao TTS requires integration with the OpenMontage TTS selector module and a valid DOUBAO_SPEECH_API_KEY, meaning it cannot function as a standalone audio synthesis tool.

Related Skills

Explore More Content & Communication Skills→
AG064AG064
2

sherpa-onnx-tts

Convert input text to speech offline using sherpa-onnx runtime.

Community
Intermediate
video-production-buddyvideo-production-buddy
602

doubao-tts

Generate Mandarin and multilingual voiceovers with word-level timestamp metadata via Volcengine Doubao Speech 2.0.

Official
Intermediate
lvhuanidlvhuanid

Podcast Generate

Generate podcast scripts and audio from text or web search results.

Community
Advanced
het8802het8802
3

doubao-tts

Generate Mandarin and multilingual voiceovers with character-level timestamps via Volcengine Doubao Speech 2.0.

Community
Intermediate