yao-audio
Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.
它会碰到什么
这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。
技能内容
Audio Tools
Use these tools to transcribe audio files to text using speech-to-text models.
audio_transcribe
Transcribe an audio file to text.
tai tool audio_transcribe --audio_path /path/to/meeting.m4atai tool audio_transcribe --audio_path /path/to/recording.wav --language en --provider llm.my-openai:whisper-1| Parameter | Type | Required | Description |
| ---------- | ------ | -------- | ----------------------------------------------------------------- |
| audio_path | string | yes | Audio file path. Supported: mp3, m4a, wav, webm, mp4, mpeg, mpga |
| language | string | no | ISO 639-1 language code (e.g. en, zh, ja). Auto-detected if omitted |
| provider | string | no | STT provider connector ID. If omitted, uses the default STT provider |
audio_providers
List available speech-to-text providers and models.
List STT providers (default):
tai tool audio_providers| Parameter | Type | Required | Description |
| ---------- | ------ | -------- | ------------------------------------ |
| capability | string | no | Filter by capability (default: audio) |
Returns a list of providers with their available models and connector IDs that can be passed to audio_transcribe.
Constraints
Only use the parameters listed above for each tool. Do not pass unsupported parameters — they will be ignored or cause errors.
想直接用这个技能？
本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。