Yichen Volc Asr logo

Yichen Volc Asr

CommunityPopular
mcncarl
yichen-volc-asr

火山引擎音视频转写 + 口播自动粗剪 skill。用于语音转文字、视频转文字、音频识别、生成时间戳/SRT 字幕,也用于帮我剪口播、自动粗剪、删重复、删停顿、删口误、生成粗剪 MP4。 触发场景:用户说"帮我转写这个视频"、"音视频转文字"、"识别这个音频"、"帮我剪口播"、"自动剪辑"时使用。

Overview

Publishermcncarl
Repositoryyichen-skills
Skill nameyichen-volc-asr
Stars
3.3K
Forks
1.4K
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mcncarl on GitHub. Read the source before you install it.

Installation

Install the Yichen Volc Asr AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mcncarl/yichen-skills.git /tmp/yichen-skills
mkdir -p .claude/skills
cp -r /tmp/yichen-skills/yichen-volc-asr .claude/skills/yichen-volc-asr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yichen Volc Asr in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Yichen Volc Asr on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Yichen Volc Asr is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

火山 ASR 转写 + 口播自动粗剪

这个 skill 同时负责两类任务:

  • 纯转写:把本地音视频识别成文字、时间戳和字幕。
  • 口播粗剪:基于 ASR 时间戳删重复、停顿、口误和废句,生成可进剪映精修的粗剪 MP4 和 SRT。

安全规则

  1. 原片不动。先复制一个工作副本,再对工作副本转写、复转写或剪辑。
  2. 不要直接删除任何文件。临时文件清理必须得到用户明确允许,并且只能先放到垃圾篓。
  3. 原片、工作副本、粗剪成片、复转写临时文件必须分开保存。
  4. 不要把 TOS、ASR Token、Cookie、API Key 写入 skill、普通记忆或日志;只从环境变量或用户指定的私有配置读取。
  5. ASR 扣费顺序固定为:先用火山控制台中仍有试用/时长包的豆包语音应用;试用/时长包确认用完后,才允许切到付费应用。试用和付费 AppID 都必须从环境变量读取,不在公开 skill 里硬编码。
  6. 试用和付费 token 必须分开:试用应用使用 VOLC_ASR_TRIAL_TOKEN,付费应用使用 VOLC_ASR_PAID_TOKEN 或旧的 VOLC_ASR_TOKEN。在试用包未用完前,不要用付费 token 冒充默认 token。
  7. 在试用/时长包未确认用完前,不得设置 VOLC_ASR_TRIAL_EXHAUSTED=1,也不得让 VOLC_ASR_APP_ID 指向付费应用;如确实要临时绕过,必须明确说明会扣费并获得用户确认。
  8. 长音频 ASR 提交成功后,不要重复跑同一文件来“再试一次”。优先等当前任务完成,或用已保存的 {工作副本}.asr_pending.json / --request-id 恢复查询,避免重复消耗试用时长或余额。

使用方法

bash
# 基础用法:转写 + 分析 + 自动剪辑
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>'

# 只看标注不执行剪辑
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --dry-run

# 忽略 ASR 缓存,重新识别
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --no-cache

# 不执行 ffmpeg 剪辑,仍生成转写、标注和 SRT
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --no-execute

# 只转写,不做剪辑分析或生成 SRT
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --transcribe-only

# 只恢复查询已提交任务,不重新上传/提交
python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --request-id '<火山ASR request_id>' --no-execute

脚本默认使用 VOLC_ASR_TRIAL_APP_ID,并优先读取 VOLC_ASR_TRIAL_TOKEN。只有确认试用/时长包已经用完后,才设置 VOLC_ASR_TRIAL_EXHAUSTED=1,脚本才会切到 VOLC_ASR_PAID_APP_ID 并读取 VOLC_ASR_PAID_TOKEN 或旧的 VOLC_ASR_TOKEN。如确实需要切到其他火山语音应用,先设置 VOLC_ASR_APP_ID;若该应用不是试用包应用且未标记试用已用完,脚本会停止,除非同时显式设置 VOLC_ASR_ALLOW_NON_TRIAL_APP=1

如果本机旧环境里只有 VOLC_ASR_TOKEN,脚本不会默认把它用于试用应用,避免 token 属于付费应用却误以为在走试用。只有确认 VOLC_ASR_TOKEN 本身就是试用 token 时,才可临时设置 VOLC_ASR_ALLOW_LEGACY_TOKEN=1 兼容旧配置。

脚本会在提交成功后写入 {工作副本}.asr_pending.json,只保存 request_id、AppID、音频 URL 和状态,不保存 token/密钥。复跑时如果没有完成缓存,会优先恢复这个未完成任务;只有明确传 --force-new 才会重新上传并提交新任务。

输出文件

文件说明
{工作副本}_cut.mp4粗剪后的视频,可导入剪映
{工作副本}_cut.srt字幕文件,剪映可导入
{工作副本}.txt完整转写文字和时间戳
{工作副本}.asr_cache.jsonASR 缓存,复跑可复用
{工作副本}.asr_pending.json未完成ASR任务记录,可用于恢复查询,不能当作完成结果

纯转写流程

  1. 确认输入文件存在、大小正常;必要时用 ffprobe 看时长和编码。
  2. 复制原片为工作副本,例如 source_for_asr.mp4
  3. 运行 python3 yichen-volc-asr/scripts/transcribe.py '<工作副本路径>' --no-execute
  4. 交付转写稿、时间戳、字幕草稿和缓存路径。
  5. 明确说明本次没有做剪辑。

口播自动粗剪流程

当用户要“帮我剪口播”“自动粗剪”“删重复/停顿/口误/断句”时:

  1. 复制原片为工作副本,避免原片被改动。
  2. 用火山 ASR 生成带时间戳的转写稿和 .asr_cache.json
  3. 写一份可读删留方案:
    • KEEP:干净、有信息量、叙事必要的内容。
    • DELETE:口误、重复、长停顿、废句、半句话、无效语气词。
    • CHECK:内容可能有用,但啰嗦或听感不确定。
  4. 用源片时间码生成删除区间或保留区间。
  5. 生成粗剪 MP4。长口播、多段删减时优先使用稳定的分段提取 + concat 流程。
  6. 对粗剪 MP4 做复转写审核。
  7. 通过审核后,输出粗剪 MP4、SRT、转写稿、删留方案和复查说明。
  8. 如需继续精修,将粗剪 MP4 和 SRT 作为交付素材,供后续导入剪映/CapCut。

剪辑规则

#规则说明
1停顿删除相邻片段时间缺口较长的静音可删除
2纯语气词删除整段仅为嗯、啊、呃、哦等语气词时删除
3相邻重复删除优先删前保后,灰色地带人工判断
4句中语气词保留语气词在句子中间时整段保留
5连续前缀词清理然后、所以、其实、就是说等连续开头时清理冗余
6短片段谨慎处理非纯语气词短片段默认保留
7智能 margin保留片段前后加缓冲,避免吞字
8Smoothing过短保留片段合并到相邻片段,避免闪帧

三层审核

每一层都检查:

  • 有没有字、短语、句子或段落级重复。
  • 有没有把完整句子剪断。
  • 有没有残留口误、废句、半句话、只有开头没有结尾的片段。
  • 有没有明显停顿、空白或节奏断裂。
  • 有没有误删承接句,导致逻辑突然跳跃。
  • 段落结构是否仍然顺。

第一层:剪前删留方案

删除区间必须对应重复、口误、废句、明显停顿或不可用残句;边界不能切进完整句子中间,除非后面有更干净的完整版本。

第二层:粗剪成片复转写

粗剪渲染后,对粗剪 MP4 重新转写。成片转写里不能有明显重复、残句、长停顿、逻辑跳跃或硬切造成的句子不完整。

第三层:最终通过

最新版粗剪必须通过一次完整审核后,才能说“可以进入剪映精修”。如果没通过,继续出新版本。

建议用一条人工确认过的粗剪成片作为质量标尺。以后口播粗剪以这个标准为基准:没有重复片段、没有明显停顿、没有把完整句子剪断。

最终回复要求

  • 纯转写:给出转写稿路径、字幕路径、缓存路径,并说明没有做剪辑。
  • 口播粗剪:给出粗剪 MP4 路径、SRT 路径、转写稿路径、删留方案路径、复查结论。
  • 如果失败,说明缺少的环境变量、文件不存在、上传失败、ASR 失败或 ffmpeg 报错。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Yichen Volc Asr AI skill do?

火山引擎音视频转写 + 口播自动粗剪 skill。用于语音转文字、视频转文字、音频识别、生成时间戳/SRT 字幕,也用于帮我剪口播、自动粗剪、删重复、删停顿、删口误、生成粗剪 MP4。 触发场景:用户说"帮我转写这个视频"、"音视频转文字"、"识别这个音频"、"帮我剪口播"、"自动剪辑"时使用。

Why use Yichen Volc Asr on TypingMind?

Because you install it once and use it with any model. Yichen Volc Asr is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Yichen Volc Asr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mcncarl/yichen-skills/tree/main/yichen-volc-asr. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Yichen Volc Asr?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Yichen Volc Asr?

As many as you like. As long as a model supports skills, you can use Yichen Volc Asr with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Yichen Volc Asr AI skill free?

It is published on GitHub by mcncarl. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇