{"enrichment":{"faq":[{"a":"Doubao TTS produces natural Mandarin and multilingual audio narration via Volcengine's Speech 2.0 API. It generates spoken audio from written text and returns word-level timing metadata for precise subtitle synchronization, making it ideal for video projects requiring accurate caption alignment.","q":"What does Doubao TTS do?"},{"a":"Yes. Doubao TTS converts text to speech using Doubao's voice synthesis capability. You can configure your voice preference and speech rate, then generate samples before committing to full narrations. The skill produces natural audio output across Mandarin and multiple languages.","q":"Can Doubao TTS convert text to speech?"},{"a":"Doubao TTS returns word-level timing metadata alongside the generated audio. This precise timing information enables accurate subtitle synchronization, allowing you to align captions exactly with the spoken content for video projects and multimedia applications.","q":"How does Doubao voice synthesis work for subtitles?"},{"a":"Doubao TTS lets you configure voice preference and speech rate to match your project needs. You can generate audio samples with your chosen settings before processing full narrations, ensuring the output meets your quality and style requirements.","q":"What customization options does Doubao TTS offer?"},{"a":"Doubao TTS produces natural audio narration in Mandarin and multiple other languages via Volcengine's Speech 2.0 API, making it suitable for diverse multilingual content creation and global video projects.","q":"Which languages does Doubao TTS support?"},{"a":"Doubao TTS is licensed under AGPL-3.0, which requires that any modifications or derivative works remain open source and available under the same license terms.","q":"What is the license for Doubao TTS?"}],"shadow_tags":["voice-synthesis","audio-generation","speech-output","text-conversion","narration-engine","voice-api","audio-service","speech-processing"],"summary_rewrite":"Doubao TTS produces natural Mandarin and multilingual audio narration via Volcengine's Speech 2.0 API. It returns word-level timing metadata for precise subtitle synchronization, making it ideal for video projects requiring accurate caption alignment. Configure your voice preference and speech rate, then generate samples before committing to full narrations."},"gist":{"api_url":"https://skillfed.io/api/skills/calesthio/OpenMontage/doubao-tts.json","as_of":"2026-07-24","description":"Doubao TTS converts text to Mandarin and multilingual speech with character-level timing for subtitles. npx skillfed install calesthio/OpenMontage/doubao-tts","install":{"manual":["git clone https://github.com/calesthio/OpenMontage","cp -r OpenMontage ~/.claude/skills/doubao-tts"],"primary":"npx skillfed install calesthio/OpenMontage/doubao-tts","version":"5efc0875"},"kind":"skill","mirror_url":"https://skillfed.io/calesthio/OpenMontage/doubao-tts.md","similar":[{"id":"calesthio/OpenMontage/dashscope","name":"Dashscope","publisher":"calesthio/OpenMontage","url":"https://skillfed.io/calesthio/OpenMontage/dashscope"},{"id":"Agents365-ai/365-skills/ttsCN","name":"Ttscn","publisher":"Agents365-ai/365-skills","url":"https://skillfed.io/Agents365-ai/365-skills/ttsCN"},{"id":"wwwzhouhui/skills_collection/article-explainer-video","name":"Article Explainer Video","publisher":"wwwzhouhui/skills_collection","url":"https://skillfed.io/wwwzhouhui/skills_collection/article-explainer-video"},{"id":"calesthio/OpenMontage/kling-official","name":"Kling Official","publisher":"calesthio/OpenMontage","url":"https://skillfed.io/calesthio/OpenMontage/kling-official"},{"id":"NoizAI/skills/tts","name":"Tts","publisher":"NoizAI/skills","url":"https://skillfed.io/NoizAI/skills/tts"}],"title":"Doubao Tts by calesthio: Generate audio narration from text \u2014 SkillFed","use":{"when":["Yes.","Doubao TTS returns word-level timing metadata alongside the generated audio."]},"what":{"lead":"Doubao TTS converts text to Mandarin and multilingual speech with character-level timing for subtitles.","rest":"Doubao TTS produces natural Mandarin and multilingual audio narration via Volcengine's Speech 2.0 API. It returns word-level timing metadata for precise subtitle synchronization, making it ideal for video projects requiring accurate caption alignment. Configure your voice preference and speech rate, then generate samples before committing to full narrations."}},"id":"calesthio/OpenMontage/doubao-tts","install":{"mode":"external","repo":"https://github.com/calesthio/OpenMontage"},"links":{"html":"https://skillfed.io/calesthio/OpenMontage/doubao-tts","md":"https://skillfed.io/calesthio/OpenMontage/doubao-tts.md","repo":"https://github.com/calesthio/OpenMontage"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":5160,"language":"Python","last_updated":"2026-07-24","license":"AGPL-3.0","name":"Doubao Tts","publisher":"calesthio","stars":42764},"relations":{"similar":[{"id":"calesthio/OpenMontage/dashscope"},{"id":"calesthio/OpenMontage/text-to-speech"},{"id":"Agents365-ai/365-skills/ttsCN"},{"id":"0xsline/OpenChatCut/voice"},{"id":"wwwzhouhui/skills_collection/article-explainer-video"},{"id":"calesthio/OpenMontage/kling-official"},{"id":"notedit/happy-skills/tts-skill"},{"id":"inference-sh/skills/text-to-speech"},{"id":"inference-sh/skills/ai-voice-cloning"},{"id":"NoizAI/skills/tts"}]},"slug":{"owner":"calesthio","repo":"OpenMontage","skill":"doubao-tts"},"version":"5efc0875"}