Generate Mandarin and multilingual narration with per-sentence timing metadata using Volcengine Doubao Speech 2.0.
npx skills add https://github.com/hanzoai/video --skill doubao-tts-hanzoai
Please help me install this Agent Skill. Skill: doubao-tts Source: https://github.com/hanzoai/video/tree/main/.agents/skills/doubao-tts Command: npx skills add https://github.com/hanzoai/video --skill doubao-tts-hanzoai
Generate high-quality Mandarin and multilingual narration for videos using Volcengine Doubao Speech 2.0, streamlining voiceover creation and subtitle-ready timing.
Generate a Mandarin narration for your video and save the audio to your project assets.
High-intent search queries and answers about installing and using this skill.
To generate Mandarin narration for a video project, this Skill automates voice synthesis using Volcengine Doubao Speech 2.0. It outputs natural-sounding audio and per-sentence subtitle timing metadata for your video assets.
Yes, Doubao TTS provides subtitle timing data for captions by returning character-level timestamps. This precise timing metadata allows you to accurately sync generated multilingual voiceovers with on-screen text.
Yes, you need a DOUBAO_SPEECH_API_KEY environment variable to use Doubao Speech 2.0 for multilingual voice synthesis. You can also configure a specific DOUBAO_SPEECH_VOICE_TYPE or provide a custom voice_id.
Yes, you can use this Skill for long-form narration generation. It supports both synchronous and asynchronous flows, allowing you to process extended Mandarin and multilingual scripts for tutorials, trailers, and narrative explainers.
To customize the voice type for Mandarin text-to-speech, set the DOUBAO_SPEECH_VOICE_TYPE environment variable or pass a specific voice_id parameter. The Skill utilizes the seed-tts-2.0 resource_id for high-quality voice selection.
47thtechcornerGenerate Mandarin and multilingual audio narration with word-level timing metadata via the Volcengine Doubao Speech 2.0 API.
video-production-buddyGenerate Mandarin and multilingual voiceovers with word-level timestamp metadata via Volcengine Doubao Speech 2.0.
JamesFincherTranscribe spoken audio into text with optional English translation and timestamps.
gyalamanch001aGenerate speech audio from text using HeyGen Starfish TTS.
