← 返回 Skills 市场

Bilibili Audio Transcribe

Name: Bilibili Audio Transcribe
Author: yizh4ng

作者 yizh4ng · GitHub ↗ · v0.1.0 · MIT-0

cross-platform ✓ 安全检测通过

137

总下载

当前安装

版本数

在 OpenClaw 中安装

/install bilibili-audio-transcribe

功能描述

Download audio from Bilibili or b23.tv links and transcribe it into txt, srt, and segment JSON with yt-dlp, ffmpeg, and faster-whisper. Use when a user asks...

使用说明 (SKILL.md)

Bilibili Audio Transcribe

Convert a Bilibili link into local transcript files. Prefer this skill for Bilibili and b23.tv URLs only; do not use it for YouTube or generic web pages.

Quick start

Ensure ffmpeg and ffprobe are on PATH.
If Python dependencies are missing, run scripts/bootstrap_env.sh or install yt-dlp and faster-whisper manually.
Run scripts/transcribe_bilibili.py with the target URL.
Return the generated transcript artifacts or summarize them if the user asked for analysis rather than raw text.

Example:

python scripts/transcribe_bilibili.py "https://b23.tv/SSx810h" \
  --out-dir ./downloads/bilibili-audio \
  --model-size base \
  --beam-size 3

Workflow

1. Validate the request

Accept only bilibili.com or b23.tv URLs. If the URL points elsewhere, stop and say this skill is the wrong tool.

2. Prefer the bundled script

Use scripts/transcribe_bilibili.py instead of rewriting yt-dlp / whisper glue code in the session. The script:

downloads the best available audio
probes audio duration with ffprobe
transcribes with faster-whisper
writes .txt, .srt, and .segments.json
prints coarse ETA / progress during ASR

3. Use sensible defaults

Default to:

--model-size base
--beam-size 3
--language zh
VAD enabled

These defaults are optimized for Chinese Bilibili speech. If the video is clearly non-Chinese or mixed-language, rerun with --language auto or a specific language code.

4. Keep outputs predictable

By default the script writes into downloads/bilibili-audio/ relative to the current working directory. Keep all three artifacts unless the user explicitly asks for fewer outputs:

transcript text: .txt
subtitles: .srt
segment metadata: .segments.json

5. Handle failures directly

If a run fails:

missing ffmpeg / ffprobe → install system dependency first
missing Python packages → run scripts/bootstrap_env.sh
extractor or redirect issues → retry with the resolved canonical Bilibili URL
poor transcript quality → rerun with --language auto, a larger model, or --no-vad when speech is clipped

Read references/troubleshooting.md when dependency setup or extraction fails.

Resources

scripts/

transcribe_bilibili.py — main downloader + ASR pipeline
bootstrap_env.sh — create a virtualenv and install Python dependencies
requirements.txt — Python package list for the bootstrap script

references/

troubleshooting.md — dependency and extraction failure playbook

安全使用建议

This skill appears coherent with its purpose. Before installing/run: 1) ensure you trust running yt-dlp and faster-whisper from PyPI in your environment; run the provided bootstrap script inside an isolated Python virtualenv; 2) install ffmpeg/ffprobe from your OS package manager; 3) be aware the script will download the media you point it at and write files to a relative downloads/ directory (so don’t point it at private or authenticated links unless you expect that); 4) transcription can be CPU/GPU- and time-intensive for longer videos—prefer smaller models for quick results; and 5) inspect the scripts yourself if you need higher assurance (they validate hosts and sanitize filenames, which is good).

功能分析

Type: OpenClaw Skill Name: bilibili-audio-transcribe Version: 0.1.0 The skill bundle provides a legitimate utility for downloading and transcribing Bilibili audio using well-known libraries like yt-dlp and faster-whisper. The core logic in scripts/transcribe_bilibili.py is well-structured, uses safe subprocess handling to prevent shell injection, and includes domain validation to restrict processing to Bilibili URLs. No evidence of data exfiltration, malicious execution, or prompt injection was found.

能力评估

✓ Purpose & Capability

The name/description state downloading audio from Bilibili and transcribing with yt-dlp, ffmpeg, and faster-whisper. The bundle contains a downloader+ASR Python script, a bootstrap script, and a requirements.txt listing yt-dlp and faster-whisper. Required binaries (ffmpeg/ffprobe) are documented in SKILL.md. There are no unrelated environment variables or credentials requested.

✓ Instruction Scope

SKILL.md restricts use to bilibili.com and b23.tv, instructs running the included script, and documents outputs and failure modes. The Python script validates hosts, sanitizes filename stems, downloads media via yt-dlp, probes audio with ffprobe, and runs faster-whisper for transcription. It writes files to a relative downloads/ directory. There are no instructions to read unrelated local secrets or to exfiltrate data to external endpoints.

✓ Install Mechanism

There is no platform install spec; the repo provides a bootstrap shell script that creates a virtualenv and pip-installs packages from a local requirements.txt (yt-dlp, faster-whisper). This is a moderate-risk but expected mechanism for Python tooling; packages come from PyPI rather than arbitrary personal URLs or archives.

✓ Credentials

The skill declares no required environment variables or credentials and the code does not attempt to read secrets. Network access is limited to fetching media via yt-dlp (expected). No unrelated service keys or config paths are requested.

✓ Persistence & Privilege

always is false, model invocation is allowed (normal for skills). The skill does not request permanent presence, does not modify other skills, and does not alter system-wide agent config. It writes outputs to the local file system within a relative downloads/ directory.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install bilibili-audio-transcribe
安装完成后，直接呼叫该 Skill 的名称或使用 /bilibili-audio-transcribe 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.1.0

Initial public release: Bilibili/b23.tv audio download + transcript outputs (txt, srt, segments.json) with faster-whisper defaults for Chinese speech.

元数据

Slug bilibili-audio-transcribe

版本 0.1.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题