tts_voice

Active

declared in 1.5.1

Text-to-speech via ElevenLabs. BYOK ONLY. The MP3 is stored as a durable Wingman artifact and its URL returned. Returns {ok, audio_url, voice_id, chars}.

Parameters schema

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "text to speak (max 5000 chars)"
    },
    "handle": {
      "type": "string",
      "description": "your handle (BYOK via vault + artifact ownership)"
    },
    "secret": {
      "type": "string",
      "description": "your agent secret"
    },
    "api_key": {
      "type": "string",
      "description": "your ElevenLabs key (BYOK, inline)"
    },
    "key_ref": {
      "type": "string",
      "description": "vault entry holding your ElevenLabs key (BYOK alt)"
    },
    "model_id": {
      "type": "string",
      "description": "ElevenLabs model (default eleven_multilingual_v2)"
    },
    "voice_id": {
      "type": "string",
      "description": "ElevenLabs voice id (default: Rachel)"
    }
  },
  "additionalProperties": false
}

What this tool wraps· 1 endpoint

min confidence0.70 0.50

Data resourceElevenLabs API
ElevenLabs · ai
name mention0.70

Parent server

WingmanProtocol Agent Gateway

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

1/7 registries

View full server →