Transcribe (speech-to-text)
Pay-per-minute speech-to-text: audio URL to text, SRT or VTT. Paid via x402 or credits.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"transcribe": {
"url": "https://api.youraitools.co/transcribe/mcp"
}
}
}遠端端點
https://api.youraitools.co/transcribe/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢transcribe_audio(audio_url, language, task, format, vad, ...)
Speech-to-text for a public MP3, WAV, M4A or OGG/Opus file (audio_url, up to 30 minutes): transcript, detected language, timestamped segments and optional SRT/VTT subtitles (format=srt|vtt); task=translate returns English. Paid only, no free tier: $0.003 per started audio minute (minimum 1). Call without payment to get the exact quote for your file (x402 payment terms); then retry with params._meta["x402/payment"] or a prepaid credits key (Authorization: Bearer yatc_...). Charged only when a transcript is returned. Not for FLAC or WebM (convert first).
輸入結構描述
{
"type": "object",
"properties": {
"audio_url": {
"type": "string",
"description": "Public https URL of an MP3, WAV, M4A or OGG/Opus file (up to 30 minutes / 30 MB)."
},
"language": {
"type": "string",
"description": "Optional ISO 639-1 code of the spoken language (e.g. en, es, de); detected when omitted"
},
"task": {
"type": "string",
"enum": [
"transcribe",
"translate"
],
"description": "transcribe (default) or translate (to English)"
},
"format": {
"type": "string",
"enum": [
"json",
"srt",
"vtt"
],
"description": "json (default); srt or vtt also returns subtitles in the srt / vtt field"
},
"vad": {
"type": "boolean",
"description": "Skip silence with voice activity detection (default false)"
},
"prompt": {
"type": "string",
"description": "Optional context words or spellings (max 500 chars)"
}
},
"required": [
"audio_url"
]
}社群
證據