Openai Whisper
OpenAI Whisper:使用 Whisper 模型进行视频语音识别和转录。
clawhub install openai-whisperTransloadit 媒体处理:Transloadit 音视频处理服务集成。
# 安装 Skill npx skills add github/awesome-copilot@transloadit-media-processing # 安装后 Claude Code 会自动识别并使用
# 同样的安装命令,兼容所有支持 SKILL.md 的 AI 编程工具 npx skills add github/awesome-copilot@transloadit-media-processing
需Transloadit付费账户和API密钥,按使用量计费
create_template, create_assembly, list_assembly_notifications, etc.)..vscode/mcp.json or user settings):{
"servers": {
"transloadit": {
"command": "npx",
"args": ["-y", "@transloadit/mcp-server", "stdio"],
"env": {
"TRANSLOADIT_KEY": "YOUR_AUTH_KEY",
"TRANSLOADIT_SECRET": "YOUR_AUTH_SECRET"
}
}
}
}
npx -y @transloadit/node assemblies create \
--steps '{"encoded": {"robot": "/video/encode", "use": ":original", "preset": "hls-1080p"}}' \
--wait \
--input ./my-video.mp4
{
"steps": {
"encoded": {
"robot": "/video/encode",
"use": ":original",
"preset": "hls-1080p"
}
}
}
{
"steps": {
"thumbnails": {
"robot": "/video/thumbs",
"use": ":original",
"count": 8,
"width": 320,
"height": 240
}
}
}
{
"steps": {
"resized": {
"robot": "/image/resize",
"use": ":original",
"width": 1200,
"height": 800,
"resize_strategy": "fit"
},
"watermarked": {
"robot": "/image/resize",
"use": "resized",
"watermark_url": "https://example.com/logo.png",
"watermark_position": "bottom-right",
"watermark_size": "15%"
}
}
}
{
"steps": {
"recognized": {
"robot": "/document/ocr",
"use": ":original",
"provider": "aws",
"format": "text"
}
}
}
{
"steps": {
"imported": {
"robot": "/http/import",
"url": ["https://example.com/clip1.mp3", "https://example.com/clip2.mp3"]
},
"concatenated": {
"robot": "/audio/concat",
"use": "imported",
"preset": "mp3"
}
}
}
"use" field. Each step references a previous step's output:{
"steps": {
"resized": {
"robot": "/image/resize",
"use": ":original",
"width": 1920
},
"optimized": {
"robot": "/image/optimize",
"use": "resized"
},
"exported": {
"robot": "/s3/store",
"use": "optimized",
"bucket": "my-bucket",
"path": "processed/${file.name}"
}
}
}
create_assembly (MCP) or assemblies create (CLI).create_template (MCP) or templates create (CLI)./video/encode, /image/resize). See full list at https://transloadit.com/docs/transcoding/:original: Refers to the uploaded input file.--wait with the CLI to block until processing completes.preset values (e.g., "hls-1080p", "mp3", "webp") for common format targets instead of specifying every parameter."use": "step_name" to build multi-step pipelines without intermediate downloads./http/import to pull files from URLs, S3, GCS, Azure, FTP, or Dropbox.${variables} for dynamic values passed at assembly creation time.npx skills add github/awesome-copilot@transloadit-media-processing && TRANSLOADIT_AUTH_KEY=xxx TRANSLOADIT_SECRET=yyy npx transloadit process --input input.mp4 --output output.mp4 --preset hd音频转录:使用本地 Whisper(Docker)将音频文件转录为文本,支持 .mp3、.m4a、.ogg、.wav、.webm 等多种格式。
Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .webm), or when asked to transcribe audio content.
clawhub install transcribe