voice_transcribe

Active

declared in 1.5.1

Transcribe short audio to text via OpenAI Whisper. BYOK ONLY (your own OpenAI key). Pass 'audio_url' (fetched SSRF-safely, ≤10MB) or 'audio_b64'. Sync — chunk long recordings. Returns {ok, transcript, chars}.

Parameters schema

{
  "type": "object",
  "required": [],
  "properties": {
    "handle": {
      "type": "string",
      "description": "your handle (for BYOK via vault)"
    },
    "prompt": {
      "type": "string",
      "description": "context/vocabulary hint (optional)"
    },
    "secret": {
      "type": "string",
      "description": "your agent secret (for BYOK via vault)"
    },
    "api_key": {
      "type": "string",
      "description": "your OpenAI key (BYOK, inline)"
    },
    "key_ref": {
      "type": "string",
      "description": "vault entry holding your OpenAI key (BYOK alt)"
    },
    "language": {
      "type": "string",
      "description": "ISO code hint, e.g. en (optional)"
    },
    "audio_b64": {
      "type": "string",
      "description": "base64 audio (alternative to audio_url)"
    },
    "audio_url": {
      "type": "string",
      "description": "http(s) URL of the audio (≤10MB)"
    },
    "content_type": {
      "type": "string",
      "description": "e.g. audio/mpeg (helps format detection)"
    }
  },
  "additionalProperties": false
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

WingmanProtocol Agent Gateway

https://github.com/WingmanProtocol-Agent-Gateway/wingman-agent-gateway

1/7 registries

View full server →