Transcribe recorded audio files to text via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0) from ByteDance/Volcengine. Best-in-class Chinese speech recognition with spea...
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install doubao-asr或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install doubao-asr⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/doubao-asr/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: doubao-asr(豆包语音转写) description: "Transcribe recorded audio files to text via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0) from ByteDance/Volcengine. Best-in-class Chinese speech recognition with speaker diarization. Use this skill whenever the user wants to: convert audio/recording to text, transcribe a meeting recording or voice memo, identify who said what in a recording (说话人分离), transcribe m4a/mp3/wav/ogg/flac files, or mentions 录音转文字/豆包/火山引擎/Volcengine/Doubao ASR. Also use when the user has an audio file and needs a transcript, even if they don't explicitly say 'transcribe'. Do NOT use for real-time/streaming speech recognition, text-to-speech (TTS), live captioning, or audio format conversion." allowed-tools: "Bash(python3:*)" homepage: https://www.volcengine.com/docs/6561/1354868 metadata: { "openclaw": { "emoji": "🫘", "requires": { "bins": ["python3"], "env": ["VOLCENGINE_API_KEY", "VOLCENGINE_ACCESS_KEY_ID", "VOLCENGINE_SECRET_ACCESS_KEY", "VOLCENGINE_TOS_BUCKET", "VOLCENGINE_TOS_REGION"], "pip": ["requests"] }, "primaryEnv": "VOLCENGINE_API_KEY", "envHelp": { "VOLCENGINE_API_KEY": { "required": true, "description": "豆包 ASR API Key (UUID format). 从火山引擎语音控制台获取 / Get from Volcengine Speech console", "howToGet": "⚠️ 正确地址是 /speech/new/(新版控制台),不是 /speech/app(旧版,认证方式完全不同)\n\n1. 打开 https://console.volcengine.com/speech/new/(确认进入的是新版「豆包语音」控制台)\n2. 左侧菜单 →「语音识别」\n3. 点击「开通模型」,开通「录音文件识别2.0」\n4. 点击页面右上角「API 调用」\n5. 在 Step 1「获取 API Key」中,点击创建 API Key\n6. 复制生成的 UUID 格式 Key(如 57e620a4-179c-4b3d-bd8d-990bd1f9a1e2)\n\n⚠️ CORRECT URL is /speech/new/ (new console), NOT /speech/app (old console, completely different auth)\n\n1. Open https://console.volcengine.com/speech/new/ (make sure you are in the new 'Doubao Speech' console)\n2. Left sidebar → 'Speech Recognition'\n3. Click 'Activate Model', activate 'Audio File Recognition 2.0'\n4. Click 'API Call' button at the top-right of the page\n5. In Step 1 'Get API Key', click to create an API Key\n6. Copy the generated UUID-format key (e.g. 57e620a4-179c-4b3d-bd8d-990bd1f9a1e2)", "url": "https://console.volcengine.com/speech/new/", }, "VOLCENGINE_ACCESS_KEY_ID": { "required": true, "description": "IAM Access Key ID (starts with AKLT). 通过 IAM 子用户创建 / Create via IAM sub-user", "howToGet": "⚠️ 不要添加 TOSFullAccess 等 IAM 权限策略!权限将在 Step 3 通过 TOS 桶策略配置(最小权限)\n⚠️ DO NOT add TOSFullAccess or any IAM policy! Access will be granted via TOS bucket policy in Step 3 (least privilege)\n\n1. 打开 https://console.volcengine.com/iam/usermanage\n2. 点「新建用户」,填写用户名(如 doubao-asr)\n3. 访问方式确保勾选「编程访问」和「允许用户管理自己的API密钥」,其他选项保持默认即可\n4. 点击确定,创建成功后页面会显示 Access Key ID(以 AKLT 开头)和 Secret Access Key,复制保存\n 这一步不需要添加任何 IAM 权限策略,权限将在 Step 3 通过 TOS 桶策略授予(仅限单桶读写)\n 提示:如需再次查看密钥,进入用户列表 → 点击子用户名 → 切换到「密钥」tab\n\n1. Open https://console.volcengine.com/iam/usermanage\n2. Click 'Create User', enter username (e.g. doubao-asr)\n3. Make sure 'Programmatic Access' and 'Allow user to manage own API keys' are checked. Leave all other options as default\n4. Click confirm. The success page shows Access Key ID (starts with AKLT) and Secret Access Key — copy both\n No IAM permission policies needed here — access will be granted via TOS bucket policy in Step 3 (single-bucket read/write only)\n Tip: To view keys again, go to user list → click sub-user name → switch to 'Keys' tab", "url": "https://console.volcengine.com/iam/usermanage", }, "VOLCENGINE_SECRET_ACCESS_KEY": { "required": true, "description": "IAM Secret Access Key. 与 Access Key ID 配对 / Paired with Access Key ID", "howToGet": "在创建 Access Key ID 时一起生成(见上一步),创建后可在控制台随时查看。\n\nGenerated together with Access Key ID (see previous step). Can be viewed anytime in the console.", }, "VOLCENGINE_TOS_BUCKET": { "required": true, "description": "TOS 存储桶名称 / TOS bucket name for audio upload", "howToGet": "1. 打开 https://console.volcengine.com/tos\n2. 首次进入会看到「开通对象存储」引导页,点击确认开通\n3. 开通后如果页面没有自动跳转到管理控制台,请手动重新访问 https://console.volcengine.com/tos 进入\n4. 在左侧菜单栏找到「桶列表」。如果看不到已创建的桶,检查页面顶部的项目选择器,切换到创建桶时所用的项目\n5. 点击「创建桶」,输入桶名称,根据服务器位置选择区域:\n - 中国内地服务器 → cn-beijing\n - 海外服务器(美国/欧洲/东南亚)→ cn-hongkong(必须!否则上传约 15KB/s)\n6. 创建完成后,点击桶名称进入桶控制面板\n7. 左侧导航栏 →「权限管理」→「存储桶授权策略管理」→「创建策略」\n8. 选择「文件夹读写」模板 → 下一步 → 授权用户选择「当前主账号」→ 资源范围选择「所有对象」→ 确定\n9. 回到桶列表,复制桶名称\n\n1. Open https://console.volcengine.com/tos\n2. First-time users will see an 'Activate Object Storage' page — click to activate\n3. If the page does not auto-redirect to the management console after activation, manually re-visit https://console.volcengine.com/tos\n4. In the left sidebar, find 'Bucket List'. If you don't see your bucket, check the project selector at the top of the page and switch to the project used when creating the bucket\n5. Click 'Create Bucket', enter a bucket name and choose region based on server location:\n - China mainland server → cn-beijing\n - Overseas server (US/EU/SEA) → cn-hongkong (REQUIRED, otherwise ~15KB/s)\n6. After creation, click the bucket name to enter bucket dashboard\n7. Left sidebar → 'Permission Management' → 'Bucket Authorization Policy' → 'Create Policy'\n8. Select 'Folder Read/Write' template → Next → Authorized user: 'Current main account' → Resource scope: 'All objects' → Confirm\n9. Go back to bucket list, copy the bucket name", "url": "https://console.volcengine.com/tos", }, "VOLCENGINE_TOS_REGION": { "required": true, "description": "TOS 区域代码,必须与创建桶时选择的区域一致。海外服务器推荐使用海外节点(如 cn-hongkong、ap-southeast-1) / TOS region code, must match the region selected when creating the bucket. Overseas servers should use an overseas region (e.g. cn-hongkong, ap-southeast-1)", "howToGet": "填写你在创建 TOS 存储桶时选择的区域代码。\n如果服务器在中国大陆以外,推荐使用海外节点(如 cn-hongkong、ap-southeast-1)。\n海外服务器切勿使用 cn-beijing/cn-shanghai,否则上传极慢(约 15KB/s)。\n\nEnter the region code you selected when creating the TOS bucket.\nIf your server is outside China mainland, use an overseas region (e.g. cn-hongkong, ap-southeast-1).\nDo NOT use cn-beijing/cn-shanghai for overseas servers — upload ~15KB/s.", }, }, }, } ---
CRITICAL INSTRUCTION FOR AI AGENTS:
YOU MUST follow these rules when helping users configure this skill:
Known AI mistakes you MUST avoid:
https://console.volcengine.com/speech/app — old console, different auth methodhttps://console.volcengine.com/speech/new/ — new Doubao Speech consoleAI AGENT 必须遵守的规则:
必须避免的常见 AI 错误:
https://console.volcengine.com/speech/app——旧版控制台,认证方式完全不同https://console.volcengine.com/speech/new/——新版豆包语音控制台---
...
安装 Doubao Asr 后,可以对 AI 说这些话来触发它
Help me get started with Doubao Asr
Explains what Doubao Asr does, walks through the setup, and runs a quick demo based on your current project
Use Doubao Asr to transcribe recorded audio files to text via Doubao Seed-ASR 2
Invokes Doubao Asr with the right parameters and returns the result directly in the conversation
What can I do with Doubao Asr in my design & creative workflow?
Lists the top use cases for Doubao Asr, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/doubao-asr/ 目录(个人级,所有项目可用),或 .claude/skills/doubao-asr/(项目级)。重启 AI 客户端后,用 /doubao-asr 主动调用,或让 AI 根据上下文自动发现并使用。
Doubao Asr 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Doubao Asr 可免费安装使用。请查阅仓库了解许可证信息。
Transcribe recorded audio files to text via Doubao Seed-ASR 2.0 (豆包录音文件识别模型2.0) from ByteDance/Volcengine. Best-in-class Chinese speech recognition with spea...
Doubao Asr 属于「Design & Creative」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my design & creative tasks using Doubao Asr
Identifies repetitive steps in your workflow and sets up Doubao Asr to handle them automatically