domains / families / media / ra-audio-to-subtitles

ra-audio-to-subtitles

separate

Generate production subtitle artifacts from the final narration audio or final merged video using Volcengine Doubao ASR word timestamps. Use for local IndexTTS2 videos, Xiaohei page videos, talking-head delivery subtitles, SRT/VTT export, or whenever subtitle timing must match the final audio. Do not use script-length interpolation for final deliverables.

When to use

• local IndexTTS2 videos
• Xiaohei page videos
• talking-head delivery subtitles
• SRT/VTT export
• subtitle timing matching final audio

When not to use

• script-length interpolation for final deliverables
• estimating final subtitle timing from character count
• estimating final subtitle timing from scene duration
• estimating final subtitle timing from TTS segment duration
• estimating final subtitle timing from fixed delays

Skill page

Source