Video to Text Bcut
Skill ActiveTranscribe video/audio URL to text + word-level timestamps using Bilibili Bcut ASR API (free, no API key). Preferred for Chinese content — Bcut gives character-level timestamps vs Whisper word-level. Returns text + segments [{start, end, text}]. Requires yt-dlp + ffmpeg.
To quickly and accurately transcribe video or audio content, especially Chinese-language media, into text with precise word-level timestamps for analysis or subtitle generation.
Features
- Transcribe video/audio URL to text
- Provide word-level timestamps
- Utilize Bilibili Bcut ASR API (free)
- Preferred for Chinese content
- Return text and segment data
Use Cases
- Generate subtitles for Chinese videos
- Extract text content from audio files
- Analyze spoken content for keywords
- Create searchable transcripts of video lectures
Non-Goals
- Real-time transcription
- Translation of transcribed text
- Handling of encrypted or private video content
- API key management for transcription services
Workflow
- Extract audio from video URL using yt-dlp
- Convert audio to 16kHz mono WAV using ffmpeg
- Upload audio to Bcut API and create transcription task
- Poll Bcut API for task completion and retrieve word-level timestamps
- Aggregate characters into sentence-level segments
- Return structured JSON output with text and segments
Practices
- Transcription
- ASR
Prerequisites
- yt-dlp
- ffmpeg
Trust
- warning:Issues AttentionOpen issues (17) are significantly higher than closed issues (3) in the last 90 days, indicating slow maintainer response to reported problems.
Installation
npx skills add 0xmariowu/AutosearchRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
Similar Extensions
Whisper
97OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Whisper
95OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
YouTube Downloader
100Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation
Summarize
99Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Cli Anything Videocaptioner
99AI-powered video captioning — transcribe speech, optimize/translate subtitles, and burn them into video via the stable VideoCaptioner backend. Free ASR and translation included.
Sheet Music Publisher
99Converts mastered audio to sheet music and creates printable songbooks. Use after mastering when the user wants sheet music or a songbook for their album.